CINXE.COM

<!DOCTYPE html> <html class="client-nojs vector-feature-language-in-header-enabled vector-feature-language-in-main-page-header-disabled vector-feature-sticky-header-disabled vector-feature-page-tools-pinned-disabled vector-feature-toc-pinned-clientpref-1 vector-feature-main-menu-pinned-disabled vector-feature-limited-width-clientpref-1 vector-feature-limited-width-content-enabled vector-feature-custom-font-size-clientpref-1 vector-feature-appearance-pinned-clientpref-1 vector-feature-night-mode-enabled skin-theme-clientpref-day vector-toc-available" lang="en" dir="ltr"> <head> <meta charset="UTF-8"> <title>Speech synthesis - Wikipedia</title> <script>(function(){var className="client-js vector-feature-language-in-header-enabled vector-feature-language-in-main-page-header-disabled vector-feature-sticky-header-disabled vector-feature-page-tools-pinned-disabled vector-feature-toc-pinned-clientpref-1 vector-feature-main-menu-pinned-disabled vector-feature-limited-width-clientpref-1 vector-feature-limited-width-content-enabled vector-feature-custom-font-size-clientpref-1 vector-feature-appearance-pinned-clientpref-1 vector-feature-night-mode-enabled skin-theme-clientpref-day vector-toc-available";var cookie=document.cookie.match(/(?:^|; )enwikimwclientpreferences=([^;]+)/);if(cookie){cookie[1].split('%2C').forEach(function(pref){className=className.replace(new RegExp('(^| )'+pref.replace(/-clientpref-\w+$|[^\w-]+/g,'')+'-clientpref-\\w+( |$)'),'$1'+pref+'$2');});}document.documentElement.className=className;}());RLCONF={"wgBreakFrames":false,"wgSeparatorTransformTable":["",""],"wgDigitTransformTable":["",""],"wgDefaultDateFormat":"dmy", "wgMonthNames":["","January","February","March","April","May","June","July","August","September","October","November","December"],"wgRequestId":"83a8e583-e116-4dab-ad24-2b07234dab6b","wgCanonicalNamespace":"","wgCanonicalSpecialPageName":false,"wgNamespaceNumber":0,"wgPageName":"Speech_synthesis","wgTitle":"Speech synthesis","wgCurRevisionId":1259199237,"wgRevisionId":1259199237,"wgArticleId":42799,"wgIsArticle":true,"wgIsRedirect":false,"wgAction":"view","wgUserName":null,"wgUserGroups":["*"],"wgCategories":["Articles with German-language sources (de)","Webarchive template wayback links","All articles with dead external links","Articles with dead external links from December 2011","CS1 maint: date and year","CS1 Polish-language sources (pl)","Articles with short description","Short description matches Wikidata","Wikipedia pending changes protected pages","Articles with hAudio microformats","All articles with unsourced statements", "Articles with unsourced statements from September 2024","Pages with plain IPA","Articles with unsourced statements from April 2016","All articles lacking reliable references","Articles lacking reliable references from July 2019","Articles containing potentially dated statements from 2016","All articles containing potentially dated statements","Articles with unsourced statements from January 2012","Articles with unsourced statements from February 2007","Articles with excerpts","Articles needing additional references from April 2023","All articles needing additional references","Articles with unsourced statements from April 2020","Articles with unsourced statements from January 2022","Articles with unsourced statements from June 2024","Commons category link from Wikidata","Speech synthesis","Applications of artificial intelligence","Assistive technology","Auditory displays","Computational linguistics","History of human–computer interaction"],"wgPageViewLanguage":"en", "wgPageContentLanguage":"en","wgPageContentModel":"wikitext","wgRelevantPageName":"Speech_synthesis","wgRelevantArticleId":42799,"wgIsProbablyEditable":true,"wgRelevantPageIsProbablyEditable":true,"wgRestrictionEdit":[],"wgRestrictionMove":[],"wgRedirectedFrom":"Text-to-speech","wgNoticeProject":"wikipedia","wgCiteReferencePreviewsActive":false,"wgFlaggedRevsParams":{"tags":{"status":{"levels":1}}},"wgStableRevisionId":1259199237,"wgMediaViewerOnClick":true,"wgMediaViewerEnabledByDefault":true,"wgPopupsFlags":0,"wgVisualEditor":{"pageLanguageCode":"en","pageLanguageDir":"ltr","pageVariantFallbacks":"en"},"wgMFDisplayWikibaseDescriptions":{"search":true,"watchlist":true,"tagline":false,"nearby":true},"wgWMESchemaEditAttemptStepOversample":false,"wgWMEPageLength":80000,"wgInternalRedirectTargetUrl":"/wiki/Speech_synthesis","wgRelatedArticlesCompat":[],"wgCentralAuthMobileDomain":false,"wgEditSubmitButtonLabelPublish":true,"wgULSPosition":"interlanguage","wgULSisCompactLinksEnabled":false ,"wgVector2022LanguageInHeader":true,"wgULSisLanguageSelectorEmpty":false,"wgWikibaseItemId":"Q16346","wgCheckUserClientHintsHeadersJsApi":["brands","architecture","bitness","fullVersionList","mobile","model","platform","platformVersion"],"GEHomepageSuggestedEditsEnableTopics":true,"wgGETopicsMatchModeEnabled":false,"wgGEStructuredTaskRejectionReasonTextInputEnabled":false,"wgGELevelingUpEnabledForUser":false};RLSTATE={"ext.globalCssJs.user.styles":"ready","site.styles":"ready","user.styles":"ready","ext.globalCssJs.user":"ready","user":"ready","user.options":"loading","ext.cite.styles":"ready","ext.tmh.player.styles":"ready","skins.vector.search.codex.styles":"ready","skins.vector.styles":"ready","skins.vector.icons":"ready","jquery.makeCollapsible.styles":"ready","ext.flaggedRevs.basic":"ready","mediawiki.codex.messagebox.styles":"ready","ext.wikimediamessages.styles":"ready","ext.visualEditor.desktopArticleTarget.noscript":"ready","ext.uls.interlanguage":"ready", "wikibase.client.init":"ready","ext.wikimediaBadges":"ready"};RLPAGEMODULES=["mediawiki.action.view.redirect","ext.cite.ux-enhancements","ext.tmh.player","mediawiki.page.media","site","mediawiki.page.ready","jquery.makeCollapsible","mediawiki.toc","skins.vector.js","ext.centralNotice.geoIP","ext.centralNotice.startUp","ext.flaggedRevs.advanced","ext.gadget.ReferenceTooltips","ext.gadget.switcher","ext.urlShortener.toolbar","ext.centralauth.centralautologin","mmv.bootstrap","ext.popups","ext.visualEditor.desktopArticleTarget.init","ext.visualEditor.targetLoader","ext.echo.centralauth","ext.eventLogging","ext.wikimediaEvents","ext.navigationTiming","ext.uls.interface","ext.cx.eventlogging.campaigns","ext.cx.uls.quick.actions","wikibase.client.vector-2022","ext.checkUser.clientHints","ext.quicksurveys.init","ext.growthExperiments.SuggestedEditSession","wikibase.sidebar.tracking"];</script> <script>(RLQ=window.RLQ||[]).push(function(){mw.loader.impl(function(){return["user.options@12s5i",function($,jQuery,require,module){mw.user.tokens.set({"patrolToken":"+\\","watchToken":"+\\","csrfToken":"+\\"}); }];});});</script> <link rel="stylesheet" href="/w/load.php?lang=en&modules=ext.cite.styles%7Cext.flaggedRevs.basic%7Cext.tmh.player.styles%7Cext.uls.interlanguage%7Cext.visualEditor.desktopArticleTarget.noscript%7Cext.wikimediaBadges%7Cext.wikimediamessages.styles%7Cjquery.makeCollapsible.styles%7Cmediawiki.codex.messagebox.styles%7Cskins.vector.icons%2Cstyles%7Cskins.vector.search.codex.styles%7Cwikibase.client.init&only=styles&skin=vector-2022"> <script async="" src="/w/load.php?lang=en&modules=startup&only=scripts&raw=1&skin=vector-2022"></script> <meta name="ResourceLoaderDynamicStyles" content=""> <link rel="stylesheet" href="/w/load.php?lang=en&modules=site.styles&only=styles&skin=vector-2022"> <meta name="generator" content="MediaWiki 1.44.0-wmf.4"> <meta name="referrer" content="origin"> <meta name="referrer" content="origin-when-cross-origin"> <meta name="robots" content="max-image-preview:standard"> <meta name="format-detection" content="telephone=no"> <meta name="viewport" content="width=1120"> <meta property="og:title" content="Speech synthesis - Wikipedia"> <meta property="og:type" content="website"> <link rel="preconnect" href="//upload.wikimedia.org"> <link rel="alternate" media="only screen and (max-width: 640px)" href="//en.m.wikipedia.org/wiki/Speech_synthesis"> <link rel="alternate" type="application/x-wiki" title="Edit this page" href="/w/index.php?title=Speech_synthesis&action=edit"> <link rel="apple-touch-icon" href="/static/apple-touch/wikipedia.png"> <link rel="icon" href="/static/favicon/wikipedia.ico"> <link rel="search" type="application/opensearchdescription+xml" href="/w/rest.php/v1/search" title="Wikipedia (en)"> <link rel="EditURI" type="application/rsd+xml" href="//en.wikipedia.org/w/api.php?action=rsd"> <link rel="canonical" href="https://en.wikipedia.org/wiki/Speech_synthesis"> <link rel="license" href="https://creativecommons.org/licenses/by-sa/4.0/deed.en"> <link rel="alternate" type="application/atom+xml" title="Wikipedia Atom feed" href="/w/index.php?title=Special:RecentChanges&feed=atom"> <link rel="dns-prefetch" href="//meta.wikimedia.org" /> <link rel="dns-prefetch" href="//login.wikimedia.org"> </head> <body class="skin--responsive skin-vector skin-vector-search-vue mediawiki ltr sitedir-ltr mw-hide-empty-elt ns-0 ns-subject mw-editable page-Speech_synthesis rootpage-Speech_synthesis skin-vector-2022 action-view"><a class="mw-jump-link" href="#bodyContent">Jump to content</a> <div class="vector-header-container"> <header class="vector-header mw-header"> <div class="vector-header-start"> <nav class="vector-main-menu-landmark" aria-label="Site"> <div id="vector-main-menu-dropdown" class="vector-dropdown vector-main-menu-dropdown vector-button-flush-left vector-button-flush-right" > <input type="checkbox" id="vector-main-menu-dropdown-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-vector-main-menu-dropdown" class="vector-dropdown-checkbox " aria-label="Main menu" > <label id="vector-main-menu-dropdown-label" for="vector-main-menu-dropdown-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only " aria-hidden="true" ><span class="vector-icon mw-ui-icon-menu mw-ui-icon-wikimedia-menu"></span> <span class="vector-dropdown-label-text">Main menu</span> </label> <div class="vector-dropdown-content"> <div id="vector-main-menu-unpinned-container" class="vector-unpinned-container"> <div id="vector-main-menu" class="vector-main-menu vector-pinnable-element"> <div class="vector-pinnable-header vector-main-menu-pinnable-header vector-pinnable-header-unpinned" data-feature-name="main-menu-pinned" data-pinnable-element-id="vector-main-menu" data-pinned-container-id="vector-main-menu-pinned-container" data-unpinned-container-id="vector-main-menu-unpinned-container" > <div class="vector-pinnable-header-label">Main menu</div> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-pin-button" data-event-name="pinnable-header.vector-main-menu.pin">move to sidebar</button> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-unpin-button" data-event-name="pinnable-header.vector-main-menu.unpin">hide</button> </div> <div id="p-navigation" class="vector-menu mw-portlet mw-portlet-navigation" > <div class="vector-menu-heading"> Navigation </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="n-mainpage-description" class="mw-list-item"><a href="/wiki/Main_Page" title="Visit the main page [z]" accesskey="z"><span>Main page</span></a></li><li id="n-contents" class="mw-list-item"><a href="/wiki/Wikipedia:Contents" title="Guides to browsing Wikipedia"><span>Contents</span></a></li><li id="n-currentevents" class="mw-list-item"><a href="/wiki/Portal:Current_events" title="Articles related to current events"><span>Current events</span></a></li><li id="n-randompage" class="mw-list-item"><a href="/wiki/Special:Random" title="Visit a randomly selected article [x]" accesskey="x"><span>Random article</span></a></li><li id="n-aboutsite" class="mw-list-item"><a href="/wiki/Wikipedia:About" title="Learn about Wikipedia and how it works"><span>About Wikipedia</span></a></li><li id="n-contactpage" class="mw-list-item"><a href="//en.wikipedia.org/wiki/Wikipedia:Contact_us" title="How to contact Wikipedia"><span>Contact us</span></a></li> </ul> </div> </div> <div id="p-interaction" class="vector-menu mw-portlet mw-portlet-interaction" > <div class="vector-menu-heading"> Contribute </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="n-help" class="mw-list-item"><a href="/wiki/Help:Contents" title="Guidance on how to use and edit Wikipedia"><span>Help</span></a></li><li id="n-introduction" class="mw-list-item"><a href="/wiki/Help:Introduction" title="Learn how to edit Wikipedia"><span>Learn to edit</span></a></li><li id="n-portal" class="mw-list-item"><a href="/wiki/Wikipedia:Community_portal" title="The hub for editors"><span>Community portal</span></a></li><li id="n-recentchanges" class="mw-list-item"><a href="/wiki/Special:RecentChanges" title="A list of recent changes to Wikipedia [r]" accesskey="r"><span>Recent changes</span></a></li><li id="n-upload" class="mw-list-item"><a href="/wiki/Wikipedia:File_upload_wizard" title="Add images or other media for use on Wikipedia"><span>Upload file</span></a></li> </ul> </div> </div> </div> </div> </div> </div> </nav> <a href="/wiki/Main_Page" class="mw-logo"> <img class="mw-logo-icon" src="/static/images/icons/wikipedia.png" alt="" aria-hidden="true" height="50" width="50"> <span class="mw-logo-container skin-invert"> <img class="mw-logo-wordmark" alt="Wikipedia" src="/static/images/mobile/copyright/wikipedia-wordmark-en.svg" style="width: 7.5em; height: 1.125em;"> <img class="mw-logo-tagline" alt="The Free Encyclopedia" src="/static/images/mobile/copyright/wikipedia-tagline-en.svg" width="117" height="13" style="width: 7.3125em; height: 0.8125em;"> </span> </a> </div> <div class="vector-header-end"> <div id="p-search" role="search" class="vector-search-box-vue vector-search-box-collapses vector-search-box-show-thumbnail vector-search-box-auto-expand-width vector-search-box"> <a href="/wiki/Special:Search" class="cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only search-toggle" title="Search Wikipedia [f]" accesskey="f"><span class="vector-icon mw-ui-icon-search mw-ui-icon-wikimedia-search"></span> <span>Search</span> </a> <div class="vector-typeahead-search-container"> <div class="cdx-typeahead-search cdx-typeahead-search--show-thumbnail cdx-typeahead-search--auto-expand-width"> <form action="/w/index.php" id="searchform" class="cdx-search-input cdx-search-input--has-end-button"> <div id="simpleSearch" class="cdx-search-input__input-wrapper" data-search-loc="header-moved"> <div class="cdx-text-input cdx-text-input--has-start-icon"> <input class="cdx-text-input__input" type="search" name="search" placeholder="Search Wikipedia" aria-label="Search Wikipedia" autocapitalize="sentences" title="Search Wikipedia [f]" accesskey="f" id="searchInput" > <span class="cdx-text-input__icon cdx-text-input__start-icon"></span> </div> <input type="hidden" name="title" value="Special:Search"> </div> <button class="cdx-button cdx-search-input__end-button">Search</button> </form> </div> </div> </div> <nav class="vector-user-links vector-user-links-wide" aria-label="Personal tools"> <div class="vector-user-links-main"> <div id="p-vector-user-menu-preferences" class="vector-menu mw-portlet emptyPortlet" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> </ul> </div> </div> <div id="p-vector-user-menu-userpage" class="vector-menu mw-portlet emptyPortlet" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> </ul> </div> </div> <nav class="vector-appearance-landmark" aria-label="Appearance"> <div id="vector-appearance-dropdown" class="vector-dropdown " title="Change the appearance of the page's font size, width, and color" > <input type="checkbox" id="vector-appearance-dropdown-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-vector-appearance-dropdown" class="vector-dropdown-checkbox " aria-label="Appearance" > <label id="vector-appearance-dropdown-label" for="vector-appearance-dropdown-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only " aria-hidden="true" ><span class="vector-icon mw-ui-icon-appearance mw-ui-icon-wikimedia-appearance"></span> <span class="vector-dropdown-label-text">Appearance</span> </label> <div class="vector-dropdown-content"> <div id="vector-appearance-unpinned-container" class="vector-unpinned-container"> </div> </div> </div> </nav> <div id="p-vector-user-menu-notifications" class="vector-menu mw-portlet emptyPortlet" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> </ul> </div> </div> <div id="p-vector-user-menu-overflow" class="vector-menu mw-portlet" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="pt-sitesupport-2" class="user-links-collapsible-item mw-list-item user-links-collapsible-item"><a data-mw="interface" href="https://donate.wikimedia.org/wiki/Special:FundraiserRedirector?utm_source=donate&utm_medium=sidebar&utm_campaign=C13_en.wikipedia.org&uselang=en" class=""><span>Donate</span></a> </li> <li id="pt-createaccount-2" class="user-links-collapsible-item mw-list-item user-links-collapsible-item"><a data-mw="interface" href="/w/index.php?title=Special:CreateAccount&returnto=Speech+synthesis" title="You are encouraged to create an account and log in; however, it is not mandatory" class=""><span>Create account</span></a> </li> <li id="pt-login-2" class="user-links-collapsible-item mw-list-item user-links-collapsible-item"><a data-mw="interface" href="/w/index.php?title=Special:UserLogin&returnto=Speech+synthesis" title="You're encouraged to log in; however, it's not mandatory. [o]" accesskey="o" class=""><span>Log in</span></a> </li> </ul> </div> </div> </div> <div id="vector-user-links-dropdown" class="vector-dropdown vector-user-menu vector-button-flush-right vector-user-menu-logged-out" title="Log in and more options" > <input type="checkbox" id="vector-user-links-dropdown-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-vector-user-links-dropdown" class="vector-dropdown-checkbox " aria-label="Personal tools" > <label id="vector-user-links-dropdown-label" for="vector-user-links-dropdown-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only " aria-hidden="true" ><span class="vector-icon mw-ui-icon-ellipsis mw-ui-icon-wikimedia-ellipsis"></span> <span class="vector-dropdown-label-text">Personal tools</span> </label> <div class="vector-dropdown-content"> <div id="p-personal" class="vector-menu mw-portlet mw-portlet-personal user-links-collapsible-item" title="User menu" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="pt-sitesupport" class="user-links-collapsible-item mw-list-item"><a href="https://donate.wikimedia.org/wiki/Special:FundraiserRedirector?utm_source=donate&utm_medium=sidebar&utm_campaign=C13_en.wikipedia.org&uselang=en"><span>Donate</span></a></li><li id="pt-createaccount" class="user-links-collapsible-item mw-list-item"><a href="/w/index.php?title=Special:CreateAccount&returnto=Speech+synthesis" title="You are encouraged to create an account and log in; however, it is not mandatory"><span class="vector-icon mw-ui-icon-userAdd mw-ui-icon-wikimedia-userAdd"></span> <span>Create account</span></a></li><li id="pt-login" class="user-links-collapsible-item mw-list-item"><a href="/w/index.php?title=Special:UserLogin&returnto=Speech+synthesis" title="You're encouraged to log in; however, it's not mandatory. [o]" accesskey="o"><span class="vector-icon mw-ui-icon-logIn mw-ui-icon-wikimedia-logIn"></span> <span>Log in</span></a></li> </ul> </div> </div> <div id="p-user-menu-anon-editor" class="vector-menu mw-portlet mw-portlet-user-menu-anon-editor" > <div class="vector-menu-heading"> Pages for logged out editors <a href="/wiki/Help:Introduction" aria-label="Learn more about editing"><span>learn more</span></a> </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="pt-anoncontribs" class="mw-list-item"><a href="/wiki/Special:MyContributions" title="A list of edits made from this IP address [y]" accesskey="y"><span>Contributions</span></a></li><li id="pt-anontalk" class="mw-list-item"><a href="/wiki/Special:MyTalk" title="Discussion about edits from this IP address [n]" accesskey="n"><span>Talk</span></a></li> </ul> </div> </div> </div> </div> </nav> </div> </header> </div> <div class="mw-page-container"> <div class="mw-page-container-inner"> <div class="vector-sitenotice-container"> <div id="siteNotice"></div> </div> <div class="vector-column-start"> <div class="vector-main-menu-container"> <div id="mw-navigation"> <nav id="mw-panel" class="vector-main-menu-landmark" aria-label="Site"> <div id="vector-main-menu-pinned-container" class="vector-pinned-container"> </div> </nav> </div> </div> <div class="vector-sticky-pinned-container"> <nav id="mw-panel-toc" aria-label="Contents" data-event-name="ui.sidebar-toc" class="mw-table-of-contents-container vector-toc-landmark"> <div id="vector-toc-pinned-container" class="vector-pinned-container"> <div id="vector-toc" class="vector-toc vector-pinnable-element"> <div class="vector-pinnable-header vector-toc-pinnable-header vector-pinnable-header-pinned" data-feature-name="toc-pinned" data-pinnable-element-id="vector-toc" > <h2 class="vector-pinnable-header-label">Contents</h2> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-pin-button" data-event-name="pinnable-header.vector-toc.pin">move to sidebar</button> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-unpin-button" data-event-name="pinnable-header.vector-toc.unpin">hide</button> </div> <ul class="vector-toc-contents" id="mw-panel-toc-list"> <li id="toc-mw-content-text" class="vector-toc-list-item vector-toc-level-1"> <a href="#" class="vector-toc-link"> <div class="vector-toc-text">(Top)</div> </a> </li> <li id="toc-History" class="vector-toc-list-item vector-toc-level-1"> <a class="vector-toc-link" href="#History"> <div class="vector-toc-text"> <span class="vector-toc-numb">1</span> <span>History</span> </div> </a> <button aria-controls="toc-History-sublist" class="cdx-button cdx-button--weight-quiet cdx-button--icon-only vector-toc-toggle"> <span class="vector-icon mw-ui-icon-wikimedia-expand"></span> <span>Toggle History subsection</span> </button> <ul id="toc-History-sublist" class="vector-toc-list"> <li id="toc-Electronic_devices" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Electronic_devices"> <div class="vector-toc-text"> <span class="vector-toc-numb">1.1</span> <span>Electronic devices</span> </div> </a> <ul id="toc-Electronic_devices-sublist" class="vector-toc-list"> </ul> </li> </ul> </li> <li id="toc-Synthesizer_technologies" class="vector-toc-list-item vector-toc-level-1"> <a class="vector-toc-link" href="#Synthesizer_technologies"> <div class="vector-toc-text"> <span class="vector-toc-numb">2</span> <span>Synthesizer technologies</span> </div> </a> <button aria-controls="toc-Synthesizer_technologies-sublist" class="cdx-button cdx-button--weight-quiet cdx-button--icon-only vector-toc-toggle"> <span class="vector-icon mw-ui-icon-wikimedia-expand"></span> <span>Toggle Synthesizer technologies subsection</span> </button> <ul id="toc-Synthesizer_technologies-sublist" class="vector-toc-list"> <li id="toc-Concatenation_synthesis" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Concatenation_synthesis"> <div class="vector-toc-text"> <span class="vector-toc-numb">2.1</span> <span>Concatenation synthesis</span> </div> </a> <ul id="toc-Concatenation_synthesis-sublist" class="vector-toc-list"> <li id="toc-Unit_selection_synthesis" class="vector-toc-list-item vector-toc-level-3"> <a class="vector-toc-link" href="#Unit_selection_synthesis"> <div class="vector-toc-text"> <span class="vector-toc-numb">2.1.1</span> <span>Unit selection synthesis</span> </div> </a> <ul id="toc-Unit_selection_synthesis-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Diphone_synthesis" class="vector-toc-list-item vector-toc-level-3"> <a class="vector-toc-link" href="#Diphone_synthesis"> <div class="vector-toc-text"> <span class="vector-toc-numb">2.1.2</span> <span>Diphone synthesis</span> </div> </a> <ul id="toc-Diphone_synthesis-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Domain-specific_synthesis" class="vector-toc-list-item vector-toc-level-3"> <a class="vector-toc-link" href="#Domain-specific_synthesis"> <div class="vector-toc-text"> <span class="vector-toc-numb">2.1.3</span> <span>Domain-specific synthesis</span> </div> </a> <ul id="toc-Domain-specific_synthesis-sublist" class="vector-toc-list"> </ul> </li> </ul> </li> <li id="toc-Formant_synthesis" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Formant_synthesis"> <div class="vector-toc-text"> <span class="vector-toc-numb">2.2</span> <span>Formant synthesis</span> </div> </a> <ul id="toc-Formant_synthesis-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Articulatory_synthesis" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Articulatory_synthesis"> <div class="vector-toc-text"> <span class="vector-toc-numb">2.3</span> <span>Articulatory synthesis</span> </div> </a> <ul id="toc-Articulatory_synthesis-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-HMM-based_synthesis" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#HMM-based_synthesis"> <div class="vector-toc-text"> <span class="vector-toc-numb">2.4</span> <span>HMM-based synthesis</span> </div> </a> <ul id="toc-HMM-based_synthesis-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Sinewave_synthesis" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Sinewave_synthesis"> <div class="vector-toc-text"> <span class="vector-toc-numb">2.5</span> <span>Sinewave synthesis</span> </div> </a> <ul id="toc-Sinewave_synthesis-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Deep_learning-based_synthesis" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Deep_learning-based_synthesis"> <div class="vector-toc-text"> <span class="vector-toc-numb">2.6</span> <span>Deep learning-based synthesis</span> </div> </a> <ul id="toc-Deep_learning-based_synthesis-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Audio_deepfakes" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Audio_deepfakes"> <div class="vector-toc-text"> <span class="vector-toc-numb">2.7</span> <span>Audio deepfakes</span> </div> </a> <ul id="toc-Audio_deepfakes-sublist" class="vector-toc-list"> </ul> </li> </ul> </li> <li id="toc-Challenges" class="vector-toc-list-item vector-toc-level-1"> <a class="vector-toc-link" href="#Challenges"> <div class="vector-toc-text"> <span class="vector-toc-numb">3</span> <span>Challenges</span> </div> </a> <button aria-controls="toc-Challenges-sublist" class="cdx-button cdx-button--weight-quiet cdx-button--icon-only vector-toc-toggle"> <span class="vector-icon mw-ui-icon-wikimedia-expand"></span> <span>Toggle Challenges subsection</span> </button> <ul id="toc-Challenges-sublist" class="vector-toc-list"> <li id="toc-Text_normalization_challenges" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Text_normalization_challenges"> <div class="vector-toc-text"> <span class="vector-toc-numb">3.1</span> <span>Text normalization challenges</span> </div> </a> <ul id="toc-Text_normalization_challenges-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Text-to-phoneme_challenges" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Text-to-phoneme_challenges"> <div class="vector-toc-text"> <span class="vector-toc-numb">3.2</span> <span>Text-to-phoneme challenges</span> </div> </a> <ul id="toc-Text-to-phoneme_challenges-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Evaluation_challenges" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Evaluation_challenges"> <div class="vector-toc-text"> <span class="vector-toc-numb">3.3</span> <span>Evaluation challenges</span> </div> </a> <ul id="toc-Evaluation_challenges-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Prosodics_and_emotional_content" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Prosodics_and_emotional_content"> <div class="vector-toc-text"> <span class="vector-toc-numb">3.4</span> <span>Prosodics and emotional content</span> </div> </a> <ul id="toc-Prosodics_and_emotional_content-sublist" class="vector-toc-list"> </ul> </li> </ul> </li> <li id="toc-Dedicated_hardware" class="vector-toc-list-item vector-toc-level-1"> <a class="vector-toc-link" href="#Dedicated_hardware"> <div class="vector-toc-text"> <span class="vector-toc-numb">4</span> <span>Dedicated hardware</span> </div> </a> <ul id="toc-Dedicated_hardware-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Hardware_and_software_systems" class="vector-toc-list-item vector-toc-level-1"> <a class="vector-toc-link" href="#Hardware_and_software_systems"> <div class="vector-toc-text"> <span class="vector-toc-numb">5</span> <span>Hardware and software systems</span> </div> </a> <button aria-controls="toc-Hardware_and_software_systems-sublist" class="cdx-button cdx-button--weight-quiet cdx-button--icon-only vector-toc-toggle"> <span class="vector-icon mw-ui-icon-wikimedia-expand"></span> <span>Toggle Hardware and software systems subsection</span> </button> <ul id="toc-Hardware_and_software_systems-sublist" class="vector-toc-list"> <li id="toc-Texas_Instruments" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Texas_Instruments"> <div class="vector-toc-text"> <span class="vector-toc-numb">5.1</span> <span>Texas Instruments</span> </div> </a> <ul id="toc-Texas_Instruments-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Mattel" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Mattel"> <div class="vector-toc-text"> <span class="vector-toc-numb">5.2</span> <span>Mattel</span> </div> </a> <ul id="toc-Mattel-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-SAM" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#SAM"> <div class="vector-toc-text"> <span class="vector-toc-numb">5.3</span> <span>SAM</span> </div> </a> <ul id="toc-SAM-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Atari" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Atari"> <div class="vector-toc-text"> <span class="vector-toc-numb">5.4</span> <span>Atari</span> </div> </a> <ul id="toc-Atari-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Apple" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Apple"> <div class="vector-toc-text"> <span class="vector-toc-numb">5.5</span> <span>Apple</span> </div> </a> <ul id="toc-Apple-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Amazon" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Amazon"> <div class="vector-toc-text"> <span class="vector-toc-numb">5.6</span> <span>Amazon</span> </div> </a> <ul id="toc-Amazon-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-AmigaOS" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#AmigaOS"> <div class="vector-toc-text"> <span class="vector-toc-numb">5.7</span> <span>AmigaOS</span> </div> </a> <ul id="toc-AmigaOS-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Microsoft_Windows" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Microsoft_Windows"> <div class="vector-toc-text"> <span class="vector-toc-numb">5.8</span> <span>Microsoft Windows</span> </div> </a> <ul id="toc-Microsoft_Windows-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Votrax" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Votrax"> <div class="vector-toc-text"> <span class="vector-toc-numb">5.9</span> <span>Votrax</span> </div> </a> <ul id="toc-Votrax-sublist" class="vector-toc-list"> </ul> </li> </ul> </li> <li id="toc-Text-to-speech_systems" class="vector-toc-list-item vector-toc-level-1"> <a class="vector-toc-link" href="#Text-to-speech_systems"> <div class="vector-toc-text"> <span class="vector-toc-numb">6</span> <span>Text-to-speech systems</span> </div> </a> <button aria-controls="toc-Text-to-speech_systems-sublist" class="cdx-button cdx-button--weight-quiet cdx-button--icon-only vector-toc-toggle"> <span class="vector-icon mw-ui-icon-wikimedia-expand"></span> <span>Toggle Text-to-speech systems subsection</span> </button> <ul id="toc-Text-to-speech_systems-sublist" class="vector-toc-list"> <li id="toc-Android" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Android"> <div class="vector-toc-text"> <span class="vector-toc-numb">6.1</span> <span>Android</span> </div> </a> <ul id="toc-Android-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Internet" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Internet"> <div class="vector-toc-text"> <span class="vector-toc-numb">6.2</span> <span>Internet</span> </div> </a> <ul id="toc-Internet-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Open_source" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Open_source"> <div class="vector-toc-text"> <span class="vector-toc-numb">6.3</span> <span>Open source</span> </div> </a> <ul id="toc-Open_source-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Others" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Others"> <div class="vector-toc-text"> <span class="vector-toc-numb">6.4</span> <span>Others</span> </div> </a> <ul id="toc-Others-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Digital_sound-alikes" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Digital_sound-alikes"> <div class="vector-toc-text"> <span class="vector-toc-numb">6.5</span> <span>Digital sound-alikes</span> </div> </a> <ul id="toc-Digital_sound-alikes-sublist" class="vector-toc-list"> </ul> </li> </ul> </li> <li id="toc-Speech_synthesis_markup_languages" class="vector-toc-list-item vector-toc-level-1"> <a class="vector-toc-link" href="#Speech_synthesis_markup_languages"> <div class="vector-toc-text"> <span class="vector-toc-numb">7</span> <span>Speech synthesis markup languages</span> </div> </a> <ul id="toc-Speech_synthesis_markup_languages-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-Applications" class="vector-toc-list-item vector-toc-level-1"> <a class="vector-toc-link" href="#Applications"> <div class="vector-toc-text"> <span class="vector-toc-numb">8</span> <span>Applications</span> </div> </a> <button aria-controls="toc-Applications-sublist" class="cdx-button cdx-button--weight-quiet cdx-button--icon-only vector-toc-toggle"> <span class="vector-icon mw-ui-icon-wikimedia-expand"></span> <span>Toggle Applications subsection</span> </button> <ul id="toc-Applications-sublist" class="vector-toc-list"> <li id="toc-Singing_synthesis" class="vector-toc-list-item vector-toc-level-2"> <a class="vector-toc-link" href="#Singing_synthesis"> <div class="vector-toc-text"> <span class="vector-toc-numb">8.1</span> <span>Singing synthesis</span> </div> </a> <ul id="toc-Singing_synthesis-sublist" class="vector-toc-list"> </ul> </li> </ul> </li> <li id="toc-See_also" class="vector-toc-list-item vector-toc-level-1"> <a class="vector-toc-link" href="#See_also"> <div class="vector-toc-text"> <span class="vector-toc-numb">9</span> <span>See also</span> </div> </a> <ul id="toc-See_also-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-References" class="vector-toc-list-item vector-toc-level-1"> <a class="vector-toc-link" href="#References"> <div class="vector-toc-text"> <span class="vector-toc-numb">10</span> <span>References</span> </div> </a> <ul id="toc-References-sublist" class="vector-toc-list"> </ul> </li> <li id="toc-External_links" class="vector-toc-list-item vector-toc-level-1"> <a class="vector-toc-link" href="#External_links"> <div class="vector-toc-text"> <span class="vector-toc-numb">11</span> <span>External links</span> </div> </a> <ul id="toc-External_links-sublist" class="vector-toc-list"> </ul> </li> </ul> </div> </div> </nav> </div> </div> <div class="mw-content-container"> <main id="content" class="mw-body"> <header class="mw-body-header vector-page-titlebar"> <nav aria-label="Contents" class="vector-toc-landmark"> <div id="vector-page-titlebar-toc" class="vector-dropdown vector-page-titlebar-toc vector-button-flush-left" > <input type="checkbox" id="vector-page-titlebar-toc-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-vector-page-titlebar-toc" class="vector-dropdown-checkbox " aria-label="Toggle the table of contents" > <label id="vector-page-titlebar-toc-label" for="vector-page-titlebar-toc-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--icon-only " aria-hidden="true" ><span class="vector-icon mw-ui-icon-listBullet mw-ui-icon-wikimedia-listBullet"></span> <span class="vector-dropdown-label-text">Toggle the table of contents</span> </label> <div class="vector-dropdown-content"> <div id="vector-page-titlebar-toc-unpinned-container" class="vector-unpinned-container"> </div> </div> </div> </nav> <h1 id="firstHeading" class="firstHeading mw-first-heading"><span class="mw-page-title-main">Speech synthesis</span></h1> <div id="p-lang-btn" class="vector-dropdown mw-portlet mw-portlet-lang" > <input type="checkbox" id="p-lang-btn-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-p-lang-btn" class="vector-dropdown-checkbox mw-interlanguage-selector" aria-label="Go to an article in another language. Available in 53 languages" > <label id="p-lang-btn-label" for="p-lang-btn-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet cdx-button--action-progressive mw-portlet-lang-heading-53" aria-hidden="true" ><span class="vector-icon mw-ui-icon-language-progressive mw-ui-icon-wikimedia-language-progressive"></span> <span class="vector-dropdown-label-text">53 languages</span> </label> <div class="vector-dropdown-content"> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li class="interlanguage-link interwiki-af mw-list-item"><a href="https://af.wikipedia.org/wiki/Spraaksintese" title="Spraaksintese – Afrikaans" lang="af" hreflang="af" data-title="Spraaksintese" data-language-autonym="Afrikaans" data-language-local-name="Afrikaans" class="interlanguage-link-target"><span>Afrikaans</span></a></li><li class="interlanguage-link interwiki-ar mw-list-item"><a href="https://ar.wikipedia.org/wiki/%D8%AA%D8%B5%D9%86%D9%8A%D8%B9_%D9%83%D9%84%D8%A7%D9%85%D9%8A" title="تصنيع كلامي – Arabic" lang="ar" hreflang="ar" data-title="تصنيع كلامي" data-language-autonym="العربية" data-language-local-name="Arabic" class="interlanguage-link-target"><span>العربية</span></a></li><li class="interlanguage-link interwiki-ast mw-list-item"><a href="https://ast.wikipedia.org/wiki/S%C3%ADntesis_de_fala" title="Síntesis de fala – Asturian" lang="ast" hreflang="ast" data-title="Síntesis de fala" data-language-autonym="Asturianu" data-language-local-name="Asturian" class="interlanguage-link-target"><span>Asturianu</span></a></li><li class="interlanguage-link interwiki-bg mw-list-item"><a href="https://bg.wikipedia.org/wiki/%D0%A0%D0%B5%D1%87%D0%B5%D0%B2%D0%B8_%D1%81%D0%B8%D0%BD%D1%82%D0%B5%D0%B7" title="Речеви синтез – Bulgarian" lang="bg" hreflang="bg" data-title="Речеви синтез" data-language-autonym="Български" data-language-local-name="Bulgarian" class="interlanguage-link-target"><span>Български</span></a></li><li class="interlanguage-link interwiki-ca mw-list-item"><a href="https://ca.wikipedia.org/wiki/S%C3%ADntesi_de_veu" title="Síntesi de veu – Catalan" lang="ca" hreflang="ca" data-title="Síntesi de veu" data-language-autonym="Català" data-language-local-name="Catalan" class="interlanguage-link-target"><span>Català</span></a></li><li class="interlanguage-link interwiki-cs mw-list-item"><a href="https://cs.wikipedia.org/wiki/Synt%C3%A9za_%C5%99e%C4%8Di" title="Syntéza řeči – Czech" lang="cs" hreflang="cs" data-title="Syntéza řeči" data-language-autonym="Čeština" data-language-local-name="Czech" class="interlanguage-link-target"><span>Čeština</span></a></li><li class="interlanguage-link interwiki-da mw-list-item"><a href="https://da.wikipedia.org/wiki/Talesyntese" title="Talesyntese – Danish" lang="da" hreflang="da" data-title="Talesyntese" data-language-autonym="Dansk" data-language-local-name="Danish" class="interlanguage-link-target"><span>Dansk</span></a></li><li class="interlanguage-link interwiki-de mw-list-item"><a href="https://de.wikipedia.org/wiki/Sprachsynthese" title="Sprachsynthese – German" lang="de" hreflang="de" data-title="Sprachsynthese" data-language-autonym="Deutsch" data-language-local-name="German" class="interlanguage-link-target"><span>Deutsch</span></a></li><li class="interlanguage-link interwiki-et mw-list-item"><a href="https://et.wikipedia.org/wiki/K%C3%B5nes%C3%BCntees" title="Kõnesüntees – Estonian" lang="et" hreflang="et" data-title="Kõnesüntees" data-language-autonym="Eesti" data-language-local-name="Estonian" class="interlanguage-link-target"><span>Eesti</span></a></li><li class="interlanguage-link interwiki-el mw-list-item"><a href="https://el.wikipedia.org/wiki/%CE%A3%CF%8D%CE%BD%CE%B8%CE%B5%CF%83%CE%B7_%CE%BF%CE%BC%CE%B9%CE%BB%CE%AF%CE%B1%CF%82" title="Σύνθεση ομιλίας – Greek" lang="el" hreflang="el" data-title="Σύνθεση ομιλίας" data-language-autonym="Ελληνικά" data-language-local-name="Greek" class="interlanguage-link-target"><span>Ελληνικά</span></a></li><li class="interlanguage-link interwiki-es mw-list-item"><a href="https://es.wikipedia.org/wiki/S%C3%ADntesis_de_habla" title="Síntesis de habla – Spanish" lang="es" hreflang="es" data-title="Síntesis de habla" data-language-autonym="Español" data-language-local-name="Spanish" class="interlanguage-link-target"><span>Español</span></a></li><li class="interlanguage-link interwiki-eo mw-list-item"><a href="https://eo.wikipedia.org/wiki/Parolsintezo" title="Parolsintezo – Esperanto" lang="eo" hreflang="eo" data-title="Parolsintezo" data-language-autonym="Esperanto" data-language-local-name="Esperanto" class="interlanguage-link-target"><span>Esperanto</span></a></li><li class="interlanguage-link interwiki-eu mw-list-item"><a href="https://eu.wikipedia.org/wiki/Hizketaren_sintesi" title="Hizketaren sintesi – Basque" lang="eu" hreflang="eu" data-title="Hizketaren sintesi" data-language-autonym="Euskara" data-language-local-name="Basque" class="interlanguage-link-target"><span>Euskara</span></a></li><li class="interlanguage-link interwiki-fa mw-list-item"><a href="https://fa.wikipedia.org/wiki/%D9%81%D8%B1%D8%A2%D9%88%D8%B1%DB%8C_%DA%AF%D9%81%D8%AA%D8%A7%D8%B1" title="فرآوری گفتار – Persian" lang="fa" hreflang="fa" data-title="فرآوری گفتار" data-language-autonym="فارسی" data-language-local-name="Persian" class="interlanguage-link-target"><span>فارسی</span></a></li><li class="interlanguage-link interwiki-fo mw-list-item"><a href="https://fo.wikipedia.org/wiki/Talusyntesa" title="Talusyntesa – Faroese" lang="fo" hreflang="fo" data-title="Talusyntesa" data-language-autonym="Føroyskt" data-language-local-name="Faroese" class="interlanguage-link-target"><span>Føroyskt</span></a></li><li class="interlanguage-link interwiki-fr mw-list-item"><a href="https://fr.wikipedia.org/wiki/Synth%C3%A8se_vocale" title="Synthèse vocale – French" lang="fr" hreflang="fr" data-title="Synthèse vocale" data-language-autonym="Français" data-language-local-name="French" class="interlanguage-link-target"><span>Français</span></a></li><li class="interlanguage-link interwiki-ko mw-list-item"><a href="https://ko.wikipedia.org/wiki/%EC%9D%8C%EC%84%B1_%ED%95%A9%EC%84%B1" title="음성 합성 – Korean" lang="ko" hreflang="ko" data-title="음성 합성" data-language-autonym="한국어" data-language-local-name="Korean" class="interlanguage-link-target"><span>한국어</span></a></li><li class="interlanguage-link interwiki-ha mw-list-item"><a href="https://ha.wikipedia.org/wiki/Speech_synthesis" title="Speech synthesis – Hausa" lang="ha" hreflang="ha" data-title="Speech synthesis" data-language-autonym="Hausa" data-language-local-name="Hausa" class="interlanguage-link-target"><span>Hausa</span></a></li><li class="interlanguage-link interwiki-hi mw-list-item"><a href="https://hi.wikipedia.org/wiki/%E0%A4%B5%E0%A4%BE%E0%A4%95%E0%A5%8D_%E0%A4%B8%E0%A4%82%E0%A4%B6%E0%A5%8D%E0%A4%B2%E0%A5%87%E0%A4%B7%E0%A4%A3" title="वाक् संश्लेषण – Hindi" lang="hi" hreflang="hi" data-title="वाक् संश्लेषण" data-language-autonym="हिन्दी" data-language-local-name="Hindi" class="interlanguage-link-target"><span>हिन्दी</span></a></li><li class="interlanguage-link interwiki-id mw-list-item"><a href="https://id.wikipedia.org/wiki/Sintesis_bunyi" title="Sintesis bunyi – Indonesian" lang="id" hreflang="id" data-title="Sintesis bunyi" data-language-autonym="Bahasa Indonesia" data-language-local-name="Indonesian" class="interlanguage-link-target"><span>Bahasa Indonesia</span></a></li><li class="interlanguage-link interwiki-is mw-list-item"><a href="https://is.wikipedia.org/wiki/Talgerving" title="Talgerving – Icelandic" lang="is" hreflang="is" data-title="Talgerving" data-language-autonym="Íslenska" data-language-local-name="Icelandic" class="interlanguage-link-target"><span>Íslenska</span></a></li><li class="interlanguage-link interwiki-it mw-list-item"><a href="https://it.wikipedia.org/wiki/Sintesi_vocale" title="Sintesi vocale – Italian" lang="it" hreflang="it" data-title="Sintesi vocale" data-language-autonym="Italiano" data-language-local-name="Italian" class="interlanguage-link-target"><span>Italiano</span></a></li><li class="interlanguage-link interwiki-he mw-list-item"><a href="https://he.wikipedia.org/wiki/%D7%A1%D7%99%D7%A0%D7%AA%D7%96%D7%AA_%D7%93%D7%99%D7%91%D7%95%D7%A8" title="סינתזת דיבור – Hebrew" lang="he" hreflang="he" data-title="סינתזת דיבור" data-language-autonym="עברית" data-language-local-name="Hebrew" class="interlanguage-link-target"><span>עברית</span></a></li><li class="interlanguage-link interwiki-kk mw-list-item"><a href="https://kk.wikipedia.org/wiki/%D0%A1%D3%A9%D0%B7_%D1%81%D0%B8%D0%BD%D1%82%D0%B5%D0%B7%D1%96" title="Сөз синтезі – Kazakh" lang="kk" hreflang="kk" data-title="Сөз синтезі" data-language-autonym="Қазақша" data-language-local-name="Kazakh" class="interlanguage-link-target"><span>Қазақша</span></a></li><li class="interlanguage-link interwiki-lv mw-list-item"><a href="https://lv.wikipedia.org/wiki/Runas_sint%C4%93ze" title="Runas sintēze – Latvian" lang="lv" hreflang="lv" data-title="Runas sintēze" data-language-autonym="Latviešu" data-language-local-name="Latvian" class="interlanguage-link-target"><span>Latviešu</span></a></li><li class="interlanguage-link interwiki-hu mw-list-item"><a href="https://hu.wikipedia.org/wiki/Besz%C3%A9dszint%C3%A9zis" title="Beszédszintézis – Hungarian" lang="hu" hreflang="hu" data-title="Beszédszintézis" data-language-autonym="Magyar" data-language-local-name="Hungarian" class="interlanguage-link-target"><span>Magyar</span></a></li><li class="interlanguage-link interwiki-ms mw-list-item"><a href="https://ms.wikipedia.org/wiki/Sintesis_pertuturan" title="Sintesis pertuturan – Malay" lang="ms" hreflang="ms" data-title="Sintesis pertuturan" data-language-autonym="Bahasa Melayu" data-language-local-name="Malay" class="interlanguage-link-target"><span>Bahasa Melayu</span></a></li><li class="interlanguage-link interwiki-my mw-list-item"><a href="https://my.wikipedia.org/wiki/%E1%80%85%E1%80%AC%E1%80%9E%E1%80%AC%E1%80%B8%E1%80%99%E1%80%BE%E1%80%A1%E1%80%9E%E1%80%B6%E1%80%95%E1%80%BC%E1%80%B1%E1%80%AC%E1%80%84%E1%80%BA%E1%80%B8%E1%80%9C%E1%80%B2%E1%80%95%E1%80%B1%E1%80%B8%E1%80%9E%E1%80%B1%E1%80%AC%E1%80%85%E1%80%94%E1%80%85%E1%80%BA" title="စာသားမှအသံပြောင်းလဲပေးသောစနစ် – Burmese" lang="my" hreflang="my" data-title="စာသားမှအသံပြောင်းလဲပေးသောစနစ်" data-language-autonym="မြန်မာဘာသာ" data-language-local-name="Burmese" class="interlanguage-link-target"><span>မြန်မာဘာသာ</span></a></li><li class="interlanguage-link interwiki-nl mw-list-item"><a href="https://nl.wikipedia.org/wiki/Spraaksynthese" title="Spraaksynthese – Dutch" lang="nl" hreflang="nl" data-title="Spraaksynthese" data-language-autonym="Nederlands" data-language-local-name="Dutch" class="interlanguage-link-target"><span>Nederlands</span></a></li><li class="interlanguage-link interwiki-ja mw-list-item"><a href="https://ja.wikipedia.org/wiki/%E9%9F%B3%E5%A3%B0%E5%90%88%E6%88%90" title="音声合成 – Japanese" lang="ja" hreflang="ja" data-title="音声合成" data-language-autonym="日本語" data-language-local-name="Japanese" class="interlanguage-link-target"><span>日本語</span></a></li><li class="interlanguage-link interwiki-no mw-list-item"><a href="https://no.wikipedia.org/wiki/Talesyntese" title="Talesyntese – Norwegian Bokmål" lang="nb" hreflang="nb" data-title="Talesyntese" data-language-autonym="Norsk bokmål" data-language-local-name="Norwegian Bokmål" class="interlanguage-link-target"><span>Norsk bokmål</span></a></li><li class="interlanguage-link interwiki-nn mw-list-item"><a href="https://nn.wikipedia.org/wiki/Talesyntese" title="Talesyntese – Norwegian Nynorsk" lang="nn" hreflang="nn" data-title="Talesyntese" data-language-autonym="Norsk nynorsk" data-language-local-name="Norwegian Nynorsk" class="interlanguage-link-target"><span>Norsk nynorsk</span></a></li><li class="interlanguage-link interwiki-pap mw-list-item"><a href="https://pap.wikipedia.org/wiki/S%C3%ADntesis_di_bos" title="Síntesis di bos – Papiamento" lang="pap" hreflang="pap" data-title="Síntesis di bos" data-language-autonym="Papiamentu" data-language-local-name="Papiamento" class="interlanguage-link-target"><span>Papiamentu</span></a></li><li class="interlanguage-link interwiki-ps mw-list-item"><a href="https://ps.wikipedia.org/wiki/%D9%88%DB%8C%D9%86%D8%A7_%D8%AA%D9%87_%D8%AF_%D9%85%D8%AA%D9%86_%D8%A7%DA%93%D9%88%D9%84" title="وینا ته د متن اړول – Pashto" lang="ps" hreflang="ps" data-title="وینا ته د متن اړول" data-language-autonym="پښتو" data-language-local-name="Pashto" class="interlanguage-link-target"><span>پښتو</span></a></li><li class="interlanguage-link interwiki-pl mw-list-item"><a href="https://pl.wikipedia.org/wiki/Synteza_mowy" title="Synteza mowy – Polish" lang="pl" hreflang="pl" data-title="Synteza mowy" data-language-autonym="Polski" data-language-local-name="Polish" class="interlanguage-link-target"><span>Polski</span></a></li><li class="interlanguage-link interwiki-pt mw-list-item"><a href="https://pt.wikipedia.org/wiki/S%C3%ADntese_de_fala" title="Síntese de fala – Portuguese" lang="pt" hreflang="pt" data-title="Síntese de fala" data-language-autonym="Português" data-language-local-name="Portuguese" class="interlanguage-link-target"><span>Português</span></a></li><li class="interlanguage-link interwiki-ru mw-list-item"><a href="https://ru.wikipedia.org/wiki/%D0%A1%D0%B8%D0%BD%D1%82%D0%B5%D0%B7_%D1%80%D0%B5%D1%87%D0%B8" title="Синтез речи – Russian" lang="ru" hreflang="ru" data-title="Синтез речи" data-language-autonym="Русский" data-language-local-name="Russian" class="interlanguage-link-target"><span>Русский</span></a></li><li class="interlanguage-link interwiki-simple mw-list-item"><a href="https://simple.wikipedia.org/wiki/Text_to_speech" title="Text to speech – Simple English" lang="en-simple" hreflang="en-simple" data-title="Text to speech" data-language-autonym="Simple English" data-language-local-name="Simple English" class="interlanguage-link-target"><span>Simple English</span></a></li><li class="interlanguage-link interwiki-sr mw-list-item"><a href="https://sr.wikipedia.org/wiki/Sinteza_govora" title="Sinteza govora – Serbian" lang="sr" hreflang="sr" data-title="Sinteza govora" data-language-autonym="Српски / srpski" data-language-local-name="Serbian" class="interlanguage-link-target"><span>Српски / srpski</span></a></li><li class="interlanguage-link interwiki-sh mw-list-item"><a href="https://sh.wikipedia.org/wiki/Sinteza_govora" title="Sinteza govora – Serbo-Croatian" lang="sh" hreflang="sh" data-title="Sinteza govora" data-language-autonym="Srpskohrvatski / српскохрватски" data-language-local-name="Serbo-Croatian" class="interlanguage-link-target"><span>Srpskohrvatski / српскохрватски</span></a></li><li class="interlanguage-link interwiki-fi mw-list-item"><a href="https://fi.wikipedia.org/wiki/Puhesynteesi" title="Puhesynteesi – Finnish" lang="fi" hreflang="fi" data-title="Puhesynteesi" data-language-autonym="Suomi" data-language-local-name="Finnish" class="interlanguage-link-target"><span>Suomi</span></a></li><li class="interlanguage-link interwiki-sv mw-list-item"><a href="https://sv.wikipedia.org/wiki/Talsyntes" title="Talsyntes – Swedish" lang="sv" hreflang="sv" data-title="Talsyntes" data-language-autonym="Svenska" data-language-local-name="Swedish" class="interlanguage-link-target"><span>Svenska</span></a></li><li class="interlanguage-link interwiki-ta mw-list-item"><a href="https://ta.wikipedia.org/wiki/%E0%AE%AA%E0%AF%87%E0%AE%9A%E0%AF%8D%E0%AE%9A%E0%AF%8A%E0%AE%B2%E0%AE%BF%E0%AE%AF%E0%AE%BE%E0%AE%95%E0%AF%8D%E0%AE%95%E0%AE%AE%E0%AF%8D" title="பேச்சொலியாக்கம் – Tamil" lang="ta" hreflang="ta" data-title="பேச்சொலியாக்கம்" data-language-autonym="தமிழ்" data-language-local-name="Tamil" class="interlanguage-link-target"><span>தமிழ்</span></a></li><li class="interlanguage-link interwiki-te mw-list-item"><a href="https://te.wikipedia.org/wiki/%E0%B0%B8%E0%B1%8D%E0%B0%AA%E0%B1%80%E0%B0%9A%E0%B1%8D_%E0%B0%B8%E0%B0%BF%E0%B0%82%E0%B0%A5%E0%B0%B8%E0%B0%BF%E0%B0%B8%E0%B1%8D" title="స్పీచ్ సింథసిస్ – Telugu" lang="te" hreflang="te" data-title="స్పీచ్ సింథసిస్" data-language-autonym="తెలుగు" data-language-local-name="Telugu" class="interlanguage-link-target"><span>తెలుగు</span></a></li><li class="interlanguage-link interwiki-th mw-list-item"><a href="https://th.wikipedia.org/wiki/%E0%B8%81%E0%B8%B2%E0%B8%A3%E0%B8%AA%E0%B8%B1%E0%B8%87%E0%B9%80%E0%B8%84%E0%B8%A3%E0%B8%B2%E0%B8%B0%E0%B8%AB%E0%B9%8C%E0%B9%80%E0%B8%AA%E0%B8%B5%E0%B8%A2%E0%B8%87%E0%B8%9E%E0%B8%B9%E0%B8%94" title="การสังเคราะห์เสียงพูด – Thai" lang="th" hreflang="th" data-title="การสังเคราะห์เสียงพูด" data-language-autonym="ไทย" data-language-local-name="Thai" class="interlanguage-link-target"><span>ไทย</span></a></li><li class="interlanguage-link interwiki-tg mw-list-item"><a href="https://tg.wikipedia.org/wiki/%D0%A1%D0%B8%D0%BD%D1%82%D0%B5%D0%B7%D0%B8_%D0%BD%D1%83%D1%82%D2%9B" title="Синтези нутқ – Tajik" lang="tg" hreflang="tg" data-title="Синтези нутқ" data-language-autonym="Тоҷикӣ" data-language-local-name="Tajik" class="interlanguage-link-target"><span>Тоҷикӣ</span></a></li><li class="interlanguage-link interwiki-tr mw-list-item"><a href="https://tr.wikipedia.org/wiki/Konu%C5%9Fma_sentezleyici" title="Konuşma sentezleyici – Turkish" lang="tr" hreflang="tr" data-title="Konuşma sentezleyici" data-language-autonym="Türkçe" data-language-local-name="Turkish" class="interlanguage-link-target"><span>Türkçe</span></a></li><li class="interlanguage-link interwiki-uk mw-list-item"><a href="https://uk.wikipedia.org/wiki/%D0%A1%D0%B8%D0%BD%D1%82%D0%B5%D0%B7_%D0%BC%D0%BE%D0%B2%D0%BB%D0%B5%D0%BD%D0%BD%D1%8F" title="Синтез мовлення – Ukrainian" lang="uk" hreflang="uk" data-title="Синтез мовлення" data-language-autonym="Українська" data-language-local-name="Ukrainian" class="interlanguage-link-target"><span>Українська</span></a></li><li class="interlanguage-link interwiki-ur mw-list-item"><a href="https://ur.wikipedia.org/wiki/%D8%AA%D8%A7%D9%84%DB%8C%D9%81_%DA%A9%D9%84%D8%A7%D9%85" title="تالیف کلام – Urdu" lang="ur" hreflang="ur" data-title="تالیف کلام" data-language-autonym="اردو" data-language-local-name="Urdu" class="interlanguage-link-target"><span>اردو</span></a></li><li class="interlanguage-link interwiki-vi mw-list-item"><a href="https://vi.wikipedia.org/wiki/T%E1%BB%95ng_h%E1%BB%A3p_gi%E1%BB%8Dng_n%C3%B3i" title="Tổng hợp giọng nói – Vietnamese" lang="vi" hreflang="vi" data-title="Tổng hợp giọng nói" data-language-autonym="Tiếng Việt" data-language-local-name="Vietnamese" class="interlanguage-link-target"><span>Tiếng Việt</span></a></li><li class="interlanguage-link interwiki-wa mw-list-item"><a href="https://wa.wikipedia.org/wiki/Sinteze_di_p%C3%A5rlaedje" title="Sinteze di pårlaedje – Walloon" lang="wa" hreflang="wa" data-title="Sinteze di pårlaedje" data-language-autonym="Walon" data-language-local-name="Walloon" class="interlanguage-link-target"><span>Walon</span></a></li><li class="interlanguage-link interwiki-zh-yue mw-list-item"><a href="https://zh-yue.wikipedia.org/wiki/%E8%AA%9E%E9%9F%B3%E5%90%88%E6%88%90" title="語音合成 – Cantonese" lang="yue" hreflang="yue" data-title="語音合成" data-language-autonym="粵語" data-language-local-name="Cantonese" class="interlanguage-link-target"><span>粵語</span></a></li><li class="interlanguage-link interwiki-zh mw-list-item"><a href="https://zh.wikipedia.org/wiki/%E8%AF%AD%E9%9F%B3%E5%90%88%E6%88%90" title="语音合成 – Chinese" lang="zh" hreflang="zh" data-title="语音合成" data-language-autonym="中文" data-language-local-name="Chinese" class="interlanguage-link-target"><span>中文</span></a></li> </ul> <div class="after-portlet after-portlet-lang"><span class="wb-langlinks-edit wb-langlinks-link"><a href="https://www.wikidata.org/wiki/Special:EntityPage/Q16346#sitelinks-wikipedia" title="Edit interlanguage links" class="wbc-editpage">Edit links</a></span></div> </div> </div> </div> </header> <div class="vector-page-toolbar"> <div class="vector-page-toolbar-container"> <div id="left-navigation"> <nav aria-label="Namespaces"> <div id="p-associated-pages" class="vector-menu vector-menu-tabs mw-portlet mw-portlet-associated-pages" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="ca-nstab-main" class="selected vector-tab-noicon mw-list-item"><a href="/wiki/Speech_synthesis" title="View the content page [c]" accesskey="c"><span>Article</span></a></li><li id="ca-talk" class="vector-tab-noicon mw-list-item"><a href="/wiki/Talk:Speech_synthesis" rel="discussion" title="Discuss improvements to the content page [t]" accesskey="t"><span>Talk</span></a></li> </ul> </div> </div> <div id="vector-variants-dropdown" class="vector-dropdown emptyPortlet" > <input type="checkbox" id="vector-variants-dropdown-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-vector-variants-dropdown" class="vector-dropdown-checkbox " aria-label="Change language variant" > <label id="vector-variants-dropdown-label" for="vector-variants-dropdown-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet" aria-hidden="true" ><span class="vector-dropdown-label-text">English</span> </label> <div class="vector-dropdown-content"> <div id="p-variants" class="vector-menu mw-portlet mw-portlet-variants emptyPortlet" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> </ul> </div> </div> </div> </div> </nav> </div> <div id="right-navigation" class="vector-collapsible"> <nav aria-label="Views"> <div id="p-views" class="vector-menu vector-menu-tabs mw-portlet mw-portlet-views" > <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="ca-view" class="selected vector-tab-noicon mw-list-item"><a href="/wiki/Speech_synthesis"><span>Read</span></a></li><li id="ca-edit" class="vector-tab-noicon mw-list-item"><a href="/w/index.php?title=Speech_synthesis&action=edit" title="Edit this page [e]" accesskey="e"><span>Edit</span></a></li><li id="ca-history" class="vector-tab-noicon mw-list-item"><a href="/w/index.php?title=Speech_synthesis&action=history" title="Past revisions of this page [h]" accesskey="h"><span>View history</span></a></li> </ul> </div> </div> </nav> <nav class="vector-page-tools-landmark" aria-label="Page tools"> <div id="vector-page-tools-dropdown" class="vector-dropdown vector-page-tools-dropdown" > <input type="checkbox" id="vector-page-tools-dropdown-checkbox" role="button" aria-haspopup="true" data-event-name="ui.dropdown-vector-page-tools-dropdown" class="vector-dropdown-checkbox " aria-label="Tools" > <label id="vector-page-tools-dropdown-label" for="vector-page-tools-dropdown-checkbox" class="vector-dropdown-label cdx-button cdx-button--fake-button cdx-button--fake-button--enabled cdx-button--weight-quiet" aria-hidden="true" ><span class="vector-dropdown-label-text">Tools</span> </label> <div class="vector-dropdown-content"> <div id="vector-page-tools-unpinned-container" class="vector-unpinned-container"> <div id="vector-page-tools" class="vector-page-tools vector-pinnable-element"> <div class="vector-pinnable-header vector-page-tools-pinnable-header vector-pinnable-header-unpinned" data-feature-name="page-tools-pinned" data-pinnable-element-id="vector-page-tools" data-pinned-container-id="vector-page-tools-pinned-container" data-unpinned-container-id="vector-page-tools-unpinned-container" > <div class="vector-pinnable-header-label">Tools</div> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-pin-button" data-event-name="pinnable-header.vector-page-tools.pin">move to sidebar</button> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-unpin-button" data-event-name="pinnable-header.vector-page-tools.unpin">hide</button> </div> <div id="p-cactions" class="vector-menu mw-portlet mw-portlet-cactions emptyPortlet vector-has-collapsible-items" title="More options" > <div class="vector-menu-heading"> Actions </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="ca-more-view" class="selected vector-more-collapsible-item mw-list-item"><a href="/wiki/Speech_synthesis"><span>Read</span></a></li><li id="ca-more-edit" class="vector-more-collapsible-item mw-list-item"><a href="/w/index.php?title=Speech_synthesis&action=edit" title="Edit this page [e]" accesskey="e"><span>Edit</span></a></li><li id="ca-more-history" class="vector-more-collapsible-item mw-list-item"><a href="/w/index.php?title=Speech_synthesis&action=history"><span>View history</span></a></li> </ul> </div> </div> <div id="p-tb" class="vector-menu mw-portlet mw-portlet-tb" > <div class="vector-menu-heading"> General </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="t-whatlinkshere" class="mw-list-item"><a href="/wiki/Special:WhatLinksHere/Speech_synthesis" title="List of all English Wikipedia pages containing links to this page [j]" accesskey="j"><span>What links here</span></a></li><li id="t-recentchangeslinked" class="mw-list-item"><a href="/wiki/Special:RecentChangesLinked/Speech_synthesis" rel="nofollow" title="Recent changes in pages linked from this page [k]" accesskey="k"><span>Related changes</span></a></li><li id="t-upload" class="mw-list-item"><a href="/wiki/Wikipedia:File_Upload_Wizard" title="Upload files [u]" accesskey="u"><span>Upload file</span></a></li><li id="t-specialpages" class="mw-list-item"><a href="/wiki/Special:SpecialPages" title="A list of all special pages [q]" accesskey="q"><span>Special pages</span></a></li><li id="t-permalink" class="mw-list-item"><a href="/w/index.php?title=Speech_synthesis&oldid=1259199237" title="Permanent link to this revision of this page"><span>Permanent link</span></a></li><li id="t-info" class="mw-list-item"><a href="/w/index.php?title=Speech_synthesis&action=info" title="More information about this page"><span>Page information</span></a></li><li id="t-cite" class="mw-list-item"><a href="/w/index.php?title=Special:CiteThisPage&page=Speech_synthesis&id=1259199237&wpFormIdentifier=titleform" title="Information on how to cite this page"><span>Cite this page</span></a></li><li id="t-urlshortener" class="mw-list-item"><a href="/w/index.php?title=Special:UrlShortener&url=https%3A%2F%2Fen.wikipedia.org%2Fwiki%2FSpeech_synthesis"><span>Get shortened URL</span></a></li><li id="t-urlshortener-qrcode" class="mw-list-item"><a href="/w/index.php?title=Special:QrCode&url=https%3A%2F%2Fen.wikipedia.org%2Fwiki%2FSpeech_synthesis"><span>Download QR code</span></a></li> </ul> </div> </div> <div id="p-coll-print_export" class="vector-menu mw-portlet mw-portlet-coll-print_export" > <div class="vector-menu-heading"> Print/export </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li id="coll-download-as-rl" class="mw-list-item"><a href="/w/index.php?title=Special:DownloadAsPdf&page=Speech_synthesis&action=show-download-screen" title="Download this page as a PDF file"><span>Download as PDF</span></a></li><li id="t-print" class="mw-list-item"><a href="/w/index.php?title=Speech_synthesis&printable=yes" title="Printable version of this page [p]" accesskey="p"><span>Printable version</span></a></li> </ul> </div> </div> <div id="p-wikibase-otherprojects" class="vector-menu mw-portlet mw-portlet-wikibase-otherprojects" > <div class="vector-menu-heading"> In other projects </div> <div class="vector-menu-content"> <ul class="vector-menu-content-list"> <li class="wb-otherproject-link wb-otherproject-commons mw-list-item"><a href="https://commons.wikimedia.org/wiki/Category:Speech_synthesis" hreflang="en"><span>Wikimedia Commons</span></a></li><li id="t-wikibase" class="wb-otherproject-link wb-otherproject-wikibase-dataitem mw-list-item"><a href="https://www.wikidata.org/wiki/Special:EntityPage/Q16346" title="Structured data on this page hosted by Wikidata [g]" accesskey="g"><span>Wikidata item</span></a></li> </ul> </div> </div> </div> </div> </div> </div> </nav> </div> </div> </div> <div class="vector-column-end"> <div class="vector-sticky-pinned-container"> <nav class="vector-page-tools-landmark" aria-label="Page tools"> <div id="vector-page-tools-pinned-container" class="vector-pinned-container"> </div> </nav> <nav class="vector-appearance-landmark" aria-label="Appearance"> <div id="vector-appearance-pinned-container" class="vector-pinned-container"> <div id="vector-appearance" class="vector-appearance vector-pinnable-element"> <div class="vector-pinnable-header vector-appearance-pinnable-header vector-pinnable-header-pinned" data-feature-name="appearance-pinned" data-pinnable-element-id="vector-appearance" data-pinned-container-id="vector-appearance-pinned-container" data-unpinned-container-id="vector-appearance-unpinned-container" > <div class="vector-pinnable-header-label">Appearance</div> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-pin-button" data-event-name="pinnable-header.vector-appearance.pin">move to sidebar</button> <button class="vector-pinnable-header-toggle-button vector-pinnable-header-unpin-button" data-event-name="pinnable-header.vector-appearance.unpin">hide</button> </div> </div> </div> </nav> </div> </div> <div id="bodyContent" class="vector-body" aria-labelledby="firstHeading" data-mw-ve-target-container> <div class="vector-body-before-content"> <div class="mw-indicators"> <div id="mw-indicator-indicator-fr-review-status" class="mw-indicator"><indicator name="fr-review-status" class="mw-fr-review-status-indicator" id="mw-fr-revision-toggle"><span class="cdx-fr-css-icon-review--status--stable"></span><b>Checked</b></indicator></div> <div id="mw-indicator-pp-autoreview" class="mw-indicator"><div class="mw-parser-output"><span typeof="mw:File"><a href="/wiki/Wikipedia:Protection_policy#pending" title="All edits by unregistered and new users are subject to review prior to becoming visible to unregistered users"><img alt="Page protected with pending changes" src="//upload.wikimedia.org/wikipedia/en/thumb/b/b7/Pending-protection-shackle.svg/20px-Pending-protection-shackle.svg.png" decoding="async" width="20" height="20" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/en/thumb/b/b7/Pending-protection-shackle.svg/30px-Pending-protection-shackle.svg.png 1.5x, //upload.wikimedia.org/wikipedia/en/thumb/b/b7/Pending-protection-shackle.svg/40px-Pending-protection-shackle.svg.png 2x" data-file-width="512" data-file-height="512" /></a></span></div></div> </div> <div id="siteSub" class="noprint">From Wikipedia, the free encyclopedia</div> </div> <div id="contentSub"><div id="mw-content-subtitle"><span class="mw-redirectedfrom">(Redirected from <a href="/w/index.php?title=Text-to-speech&redirect=no" class="mw-redirect" title="Text-to-speech">Text-to-speech</a>)</span><br /> <div id="mw-fr-revision-messages"><div id="mw-fr-revision-details" class="mw-fr-revision-details-dialog" style="display:none;"><div tabindex="0"></div><div class="cdx-dialog cdx-dialog--horizontal-actions"><header class="cdx-dialog__header cdx-dialog__header--default"><div class="cdx-dialog__header__title-group"><h2 class="cdx-dialog__header__title">Page version status</h2><p class="cdx-dialog__header__subtitle">This is an accepted version of this page</p></div><button class="cdx-button cdx-button--action-default cdx-button--weight-quiet
							cdx-button--size-medium cdx-button--icon-only cdx-dialog__header__close-button" aria-label="Close" onclick="document.getElementById("mw-fr-revision-details").style.display = "none";" type="submit"><span class="cdx-icon cdx-icon--medium
							cdx-fr-css-icon--close"></span></button></header><div class="cdx-dialog__body">This is the <a href="/wiki/Wikipedia:Pending_changes" title="Wikipedia:Pending changes">latest accepted revision</a>, <a class="external text" href="https://en.wikipedia.org/w/index.php?title=Special:Log&type=review&page=Speech_synthesis">reviewed</a> on <i>23 November 2024</i>.</div></div><div tabindex="0"></div></div></div></div></div> <div id="mw-content-text" class="mw-body-content"><div class="mw-content-ltr mw-parser-output" lang="en" dir="ltr"><div class="shortdescription nomobile noexcerpt noprint searchaux" style="display:none">Artificial production of human speech</div> <p class="mw-empty-elt"> </p> <style data-mw-deduplicate="TemplateStyles:r1235681985">.mw-parser-output .side-box{margin:4px 0;box-sizing:border-box;border:1px solid #aaa;font-size:88%;line-height:1.25em;background-color:var(--background-color-interactive-subtle,#f8f9fa);display:flow-root}.mw-parser-output .side-box-abovebelow,.mw-parser-output .side-box-text{padding:0.25em 0.9em}.mw-parser-output .side-box-image{padding:2px 0 2px 0.9em;text-align:center}.mw-parser-output .side-box-imageright{padding:2px 0.9em 2px 0;text-align:center}@media(min-width:500px){.mw-parser-output .side-box-flex{display:flex;align-items:center}.mw-parser-output .side-box-text{flex:1;min-width:0}}@media(min-width:720px){.mw-parser-output .side-box{width:238px}.mw-parser-output .side-box-right{clear:right;float:right;margin-left:1em}.mw-parser-output .side-box-left{margin-right:1em}}</style><style data-mw-deduplicate="TemplateStyles:r1096940132">.mw-parser-output .listen .side-box-text{line-height:1.1em}.mw-parser-output .listen-plain{border:none;background:transparent}.mw-parser-output .listen-embedded{width:100%;margin:0;border-width:1px 0 0 0;background:transparent}.mw-parser-output .listen-header{padding:2px}.mw-parser-output .listen-embedded .listen-header{padding:2px 0}.mw-parser-output .listen-file-header{padding:4px 0}.mw-parser-output .listen .description{padding-top:2px}.mw-parser-output .listen .mw-tmh-player{max-width:100%}@media(max-width:719px){.mw-parser-output .listen{clear:both}}@media(min-width:720px){.mw-parser-output .listen:not(.listen-noimage){width:320px}.mw-parser-output .listen-left{overflow:visible;float:left}.mw-parser-output .listen-center{float:none;margin-left:auto;margin-right:auto}}</style><div class="side-box side-box-right listen noprint"><style data-mw-deduplicate="TemplateStyles:r1126788409">.mw-parser-output .plainlist ol,.mw-parser-output .plainlist ul{line-height:inherit;list-style:none;margin:0;padding:0}.mw-parser-output .plainlist ol li,.mw-parser-output .plainlist ul li{margin-bottom:0}</style> <div class="side-box-flex"> <div class="side-box-image"><figure class="mw-halign-center" typeof="mw:File"><span><img alt="" src="//upload.wikimedia.org/wikipedia/commons/thumb/8/87/Gnome-mime-sound-openclipart.svg/50px-Gnome-mime-sound-openclipart.svg.png" decoding="async" width="50" height="50" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/8/87/Gnome-mime-sound-openclipart.svg/75px-Gnome-mime-sound-openclipart.svg.png 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/8/87/Gnome-mime-sound-openclipart.svg/100px-Gnome-mime-sound-openclipart.svg.png 2x" data-file-width="160" data-file-height="160" /></span><figcaption></figcaption></figure></div> <div class="side-box-text plainlist"><div class="haudio"> <div class="listen-file-header"><a href="/wiki/File:J%C3%A4rDa-utrop.ogg" title="File:JärDa-utrop.ogg">Automatic announcement</a></div> <div><span typeof="mw:File"><span><audio id="mwe_player_0" controls="" preload="none" data-mw-tmh="" class="mw-file-element" width="232" style="width:232px;" data-durationhint="44" data-mwtitle="JärDa-utrop.ogg" data-mwprovider="wikimediacommons"><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/1/11/J%C3%A4rDa-utrop.ogg/J%C3%A4rDa-utrop.ogg.mp3" type="audio/mpeg" data-transcodekey="mp3" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/1/11/J%C3%A4rDa-utrop.ogg" type="audio/ogg; codecs="vorbis"" data-width="0" data-height="0" /><track src="https://commons.wikimedia.org/w/api.php?action=timedtext&title=File%3AJ%C3%A4rDa-utrop.ogg&lang=en&trackformat=vtt&origin=%2A" kind="subtitles" type="text/vtt" srclang="en" label="English ‪(en)‬" data-dir="ltr" /><track src="https://commons.wikimedia.org/w/api.php?action=timedtext&title=File%3AJ%C3%A4rDa-utrop.ogg&lang=sv&trackformat=vtt&origin=%2A" kind="subtitles" type="text/vtt" srclang="sv" label="svenska ‪(sv)‬" data-dir="ltr" /></audio></span></span></div> <div class="description">A synthetic voice announcing an arriving train in Sweden.</div></div></div></div> <div class="side-box-abovebelow"><hr /><i class="selfreference">Problems playing this file? See <a href="/wiki/Help:Media" title="Help:Media">media help</a>.</i></div> </div> <p><b>Speech synthesis</b> is the artificial production of human <a href="/wiki/Speech" title="Speech">speech</a>. A computer system used for this purpose is called a <b>speech synthesizer</b>, and can be implemented in <a href="/wiki/Software" title="Software">software</a> or <a href="/wiki/Computer_hardware" title="Computer hardware">hardware</a> products. A <b>text-to-speech</b> (<b>TTS</b>) system converts normal language text into speech; other systems render <a href="/wiki/Symbolic_linguistic_representation" title="Symbolic linguistic representation">symbolic linguistic representations</a> like <a href="/wiki/Phonetic_transcription" title="Phonetic transcription">phonetic transcriptions</a> into speech.<sup id="cite_ref-1" class="reference"><a href="#cite_note-1"><span class="cite-bracket">[</span>1<span class="cite-bracket">]</span></a></sup> The reverse process is <a href="/wiki/Speech_recognition" title="Speech recognition">speech recognition</a>. </p><p>Synthesized speech can be created by <a href="/wiki/Concatenative_synthesis" title="Concatenative synthesis">concatenating</a> pieces of recorded speech that are stored in a <a href="/wiki/Database" title="Database">database</a>. Systems differ in the size of the stored speech units; a system that stores <a href="/wiki/Phone_(phonetics)" title="Phone (phonetics)">phones</a> or <a href="/wiki/Diphone" title="Diphone">diphones</a> provides the largest output range, but may lack clarity.<sup class="noprint Inline-Template Template-Fact" style="white-space:nowrap;">[<i><a href="/wiki/Wikipedia:Citation_needed" title="Wikipedia:Citation needed"><span title="This claim needs references to reliable sources. (September 2024)">citation needed</span></a></i>]</sup> For specific usage domains, the storage of entire words or sentences allows for high-quality output. Alternatively, a synthesizer can incorporate a model of the <a href="/wiki/Vocal_tract" title="Vocal tract">vocal tract</a> and other human voice characteristics to create a completely "synthetic" voice output.<sup id="cite_ref-2" class="reference"><a href="#cite_note-2"><span class="cite-bracket">[</span>2<span class="cite-bracket">]</span></a></sup> </p><p>The quality of a speech synthesizer is judged by its similarity to the human voice and by its ability to be understood clearly. An intelligible text-to-speech program allows people with <a href="/wiki/Visual_impairment" title="Visual impairment">visual impairments</a> or <a href="/wiki/Reading_disability" title="Reading disability">reading disabilities</a> to listen to written words on a home computer. Many computer <a href="/wiki/Operating_system" title="Operating system">operating systems</a> have included speech synthesizers since the early 1990s.<sup class="noprint Inline-Template Template-Fact" style="white-space:nowrap;">[<i><a href="/wiki/Wikipedia:Citation_needed" title="Wikipedia:Citation needed"><span title="This claim needs references to reliable sources. (September 2024)">citation needed</span></a></i>]</sup> </p> <figure typeof="mw:File/Thumb"><a href="/wiki/File:TTS_System.svg" class="mw-file-description"><img src="//upload.wikimedia.org/wikipedia/commons/thumb/b/b5/TTS_System.svg/550px-TTS_System.svg.png" decoding="async" width="550" height="165" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/b/b5/TTS_System.svg/825px-TTS_System.svg.png 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/b/b5/TTS_System.svg/1100px-TTS_System.svg.png 2x" data-file-width="700" data-file-height="210" /></a><figcaption>Overview of a typical TTS system</figcaption></figure> <p>A text-to-speech system (or "engine") is composed of two parts:<sup id="cite_ref-3" class="reference"><a href="#cite_note-3"><span class="cite-bracket">[</span>3<span class="cite-bracket">]</span></a></sup> a <a href="/wiki/Input_method" title="Input method">front-end</a> and a <a href="/wiki/Front_and_back_ends" class="mw-redirect" title="Front and back ends">back-end</a>. The front-end has two major tasks. First, it converts raw text containing symbols like numbers and abbreviations into the equivalent of written-out words. This process is often called <i><a href="/wiki/Text_normalization" title="Text normalization">text normalization</a></i>, <i>pre-processing</i>, or <i><a href="/wiki/Tokenization_(lexical_analysis)" class="mw-redirect" title="Tokenization (lexical analysis)">tokenization</a></i>. The front-end then assigns <a href="/wiki/Phonetic_transcription" title="Phonetic transcription">phonetic transcriptions</a> to each word, and divides and marks the text into <a href="/wiki/Prosody_(linguistics)" title="Prosody (linguistics)">prosodic units</a>, like <a href="/wiki/Phrase" title="Phrase">phrases</a>, <a href="/wiki/Clause" title="Clause">clauses</a>, and <a href="/wiki/Sentence_(linguistics)" title="Sentence (linguistics)">sentences</a>. The process of assigning phonetic transcriptions to words is called <i>text-to-phoneme</i> or <i><a href="/wiki/Grapheme" title="Grapheme">grapheme</a>-to-phoneme</i> conversion. Phonetic transcriptions and <a href="/wiki/Prosody_(linguistics)" title="Prosody (linguistics)">prosody</a> information together make up the symbolic linguistic representation that is output by the front-end. The back-end—often referred to as the <i>synthesizer</i>—then converts the symbolic linguistic representation into sound. In certain systems, this part includes the computation of the <i>target prosody</i> (pitch contour, phoneme durations),<sup id="cite_ref-4" class="reference"><a href="#cite_note-4"><span class="cite-bracket">[</span>4<span class="cite-bracket">]</span></a></sup> which is then imposed on the output speech. </p> <meta property="mw:PageProp/toc" /> <div class="mw-heading mw-heading2"><h2 id="History">History</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=1" title="Edit section: History"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>Long before the invention of <a href="/wiki/Electronics" title="Electronics">electronic</a> <a href="/wiki/Signal_processing" title="Signal processing">signal processing</a>, some people tried to build machines to emulate human speech. Some early legends of the existence of "<a href="/wiki/Brazen_Head" class="mw-redirect" title="Brazen Head">Brazen Heads</a>" involved Pope <a href="/wiki/Silvester_II" class="mw-redirect" title="Silvester II">Silvester II</a> (d. 1003 AD), <a href="/wiki/Albertus_Magnus" title="Albertus Magnus">Albertus Magnus</a> (1198–1280), and <a href="/wiki/Roger_Bacon" title="Roger Bacon">Roger Bacon</a> (1214–1294). </p><p>In 1779, the <a href="/wiki/Germany" title="Germany">German</a>-<a href="/wiki/Denmark" title="Denmark">Danish</a> scientist <a href="/wiki/Christian_Gottlieb_Kratzenstein" title="Christian Gottlieb Kratzenstein">Christian Gottlieb Kratzenstein</a> won the first prize in a competition announced by the Russian <a href="/wiki/Russian_Academy_of_Sciences" title="Russian Academy of Sciences">Imperial Academy of Sciences and Arts</a> for models he built of the human <a href="/wiki/Vocal_tract" title="Vocal tract">vocal tract</a> that could produce the five long <a href="/wiki/Vowel" title="Vowel">vowel</a> sounds (in <a href="/wiki/International_Phonetic_Alphabet" title="International Phonetic Alphabet">International Phonetic Alphabet</a> notation: <span class="IPA nowrap" lang="und-Latn-fonipa" title="Representation in the International Phonetic Alphabet (IPA)">[aː]</span>, <span class="IPA nowrap" lang="und-Latn-fonipa" title="Representation in the International Phonetic Alphabet (IPA)">[eː]</span>, <span class="IPA nowrap" lang="und-Latn-fonipa" title="Representation in the International Phonetic Alphabet (IPA)">[iː]</span>, <span class="IPA nowrap" lang="und-Latn-fonipa" title="Representation in the International Phonetic Alphabet (IPA)">[oː]</span> and <span class="IPA nowrap" lang="und-Latn-fonipa" title="Representation in the International Phonetic Alphabet (IPA)">[uː]</span>).<sup id="cite_ref-Helsinki_5-0" class="reference"><a href="#cite_note-Helsinki-5"><span class="cite-bracket">[</span>5<span class="cite-bracket">]</span></a></sup> There followed the <a href="/wiki/Bellows" title="Bellows">bellows</a>-operated "<a href="/wiki/Wolfgang_von_Kempelen%27s_Speaking_Machine" class="mw-redirect" title="Wolfgang von Kempelen's Speaking Machine">acoustic-mechanical speech machine</a>" of <a href="/wiki/Wolfgang_von_Kempelen" title="Wolfgang von Kempelen">Wolfgang von Kempelen</a> of <a href="/wiki/Pressburg" class="mw-redirect" title="Pressburg">Pressburg</a>, Hungary, described in a 1791 paper.<sup id="cite_ref-6" class="reference"><a href="#cite_note-6"><span class="cite-bracket">[</span>6<span class="cite-bracket">]</span></a></sup> This machine added models of the tongue and lips, enabling it to produce consonants as well as vowels. In 1837, <a href="/wiki/Charles_Wheatstone" title="Charles Wheatstone">Charles Wheatstone</a> produced a "speaking machine" based on von Kempelen's design, and in 1846, Joseph Faber exhibited the "<a href="/wiki/Euphonia_(device)" title="Euphonia (device)">Euphonia</a>". In 1923, Paget resurrected Wheatstone's design.<sup id="cite_ref-7" class="reference"><a href="#cite_note-7"><span class="cite-bracket">[</span>7<span class="cite-bracket">]</span></a></sup> </p><p>In the 1930s, <a href="/wiki/Bell_Labs" title="Bell Labs">Bell Labs</a> developed the <a href="/wiki/Vocoder" title="Vocoder">vocoder</a>, which automatically analyzed speech into its fundamental tones and resonances. From his work on the vocoder, <a href="/wiki/Homer_Dudley" title="Homer Dudley">Homer Dudley</a> developed a keyboard-operated voice-synthesizer called <a href="/wiki/The_Voder" class="mw-redirect" title="The Voder">The Voder</a> (Voice Demonstrator), which he exhibited at the <a href="/wiki/1939_New_York_World%27s_Fair" title="1939 New York World's Fair">1939 New York World's Fair</a>. </p><p><a href="/wiki/Franklin_S._Cooper" title="Franklin S. Cooper">Dr. Franklin S. Cooper</a> and his colleagues at <a href="/wiki/Haskins_Laboratories" title="Haskins Laboratories">Haskins Laboratories</a> built the <a href="/wiki/Pattern_playback" title="Pattern playback">Pattern playback</a> in the late 1940s and completed it in 1950. There were several different versions of this hardware device; only one currently survives. The machine converts pictures of the acoustic patterns of speech in the form of a spectrogram back into sound. Using this device, <a href="/wiki/Alvin_Liberman" title="Alvin Liberman">Alvin Liberman</a> and colleagues discovered acoustic cues for the perception of <a href="/wiki/Phonetic" class="mw-redirect" title="Phonetic">phonetic</a> segments (consonants and vowels). </p> <div class="mw-heading mw-heading3"><h3 id="Electronic_devices">Electronic devices</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=2" title="Edit section: Electronic devices"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <figure class="mw-default-size" typeof="mw:File/Thumb"><a href="/wiki/File:Computer_and_speech_synthesiser_housing,_19_(9663804888).jpg" class="mw-file-description"><img src="//upload.wikimedia.org/wikipedia/commons/thumb/e/ec/Computer_and_speech_synthesiser_housing%2C_19_%289663804888%29.jpg/220px-Computer_and_speech_synthesiser_housing%2C_19_%289663804888%29.jpg" decoding="async" width="220" height="264" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/e/ec/Computer_and_speech_synthesiser_housing%2C_19_%289663804888%29.jpg/330px-Computer_and_speech_synthesiser_housing%2C_19_%289663804888%29.jpg 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/e/ec/Computer_and_speech_synthesiser_housing%2C_19_%289663804888%29.jpg/440px-Computer_and_speech_synthesiser_housing%2C_19_%289663804888%29.jpg 2x" data-file-width="1040" data-file-height="1250" /></a><figcaption> Computer and speech synthesizer housing used by <a href="/wiki/Stephen_Hawking" title="Stephen Hawking">Stephen Hawking</a> in 1999</figcaption></figure> <p>The first computer-based speech-synthesis systems originated in the late 1950s. Noriko Umeda <i>et al.</i> developed the first general English text-to-speech system in 1968, at the <a href="/wiki/Electrotechnical_Laboratory" class="mw-redirect" title="Electrotechnical Laboratory">Electrotechnical Laboratory</a> in Japan.<sup id="cite_ref-8" class="reference"><a href="#cite_note-8"><span class="cite-bracket">[</span>8<span class="cite-bracket">]</span></a></sup> In 1961, physicist <a href="/wiki/John_Larry_Kelly,_Jr" class="mw-redirect" title="John Larry Kelly, Jr">John Larry Kelly, Jr</a> and his colleague <a href="/wiki/Louis_Gerstman" title="Louis Gerstman">Louis Gerstman</a><sup id="cite_ref-9" class="reference"><a href="#cite_note-9"><span class="cite-bracket">[</span>9<span class="cite-bracket">]</span></a></sup> used an <a href="/wiki/IBM_704" title="IBM 704">IBM 704</a> computer to synthesize speech, an event among the most prominent in the history of <a href="/wiki/Bell_Labs" title="Bell Labs">Bell Labs</a>.<sup class="noprint Inline-Template Template-Fact" style="white-space:nowrap;">[<i><a href="/wiki/Wikipedia:Citation_needed" title="Wikipedia:Citation needed"><span title="This claim needs references to reliable sources. (April 2016)">citation needed</span></a></i>]</sup> Kelly's voice recorder synthesizer (<a href="/wiki/Vocoder" title="Vocoder">vocoder</a>) recreated the song "<a href="/wiki/Daisy_Bell" title="Daisy Bell">Daisy Bell</a>", with musical accompaniment from <a href="/wiki/Max_Mathews" title="Max Mathews">Max Mathews</a>. Coincidentally, <a href="/wiki/Arthur_C._Clarke" title="Arthur C. Clarke">Arthur C. Clarke</a> was visiting his friend and colleague John Pierce at the Bell Labs Murray Hill facility. Clarke was so impressed by the demonstration that he used it in the climactic scene of his screenplay for his novel <i><a href="/wiki/2001:_A_Space_Odyssey_(novel)" title="2001: A Space Odyssey (novel)">2001: A Space Odyssey</a></i>,<sup id="cite_ref-10" class="reference"><a href="#cite_note-10"><span class="cite-bracket">[</span>10<span class="cite-bracket">]</span></a></sup> where the <a href="/wiki/HAL_9000" title="HAL 9000">HAL 9000</a> computer sings the same song as astronaut <a href="/wiki/David_Bowman_(Space_Odyssey)" class="mw-redirect" title="David Bowman (Space Odyssey)">Dave Bowman</a> puts it to sleep.<sup id="cite_ref-11" class="reference"><a href="#cite_note-11"><span class="cite-bracket">[</span>11<span class="cite-bracket">]</span></a></sup> Despite the success of purely electronic speech synthesis, research into mechanical speech-synthesizers continues.<sup id="cite_ref-12" class="reference"><a href="#cite_note-12"><span class="cite-bracket">[</span>12<span class="cite-bracket">]</span></a></sup><sup class="noprint Inline-Template noprint Template-Fact" style="white-space:nowrap;">[<i><a href="/wiki/Wikipedia:Independent_sources" title="Wikipedia:Independent sources"><span title="This claim needs a reference to a independent, third-party source. (July 2019)">third-party source needed</span></a></i>]</sup> </p><p><a href="/wiki/Linear_predictive_coding" title="Linear predictive coding">Linear predictive coding</a> (LPC), a form of <a href="/wiki/Speech_coding" title="Speech coding">speech coding</a>, began development with the work of <a href="/wiki/Fumitada_Itakura" title="Fumitada Itakura">Fumitada Itakura</a> of <a href="/wiki/Nagoya_University" title="Nagoya University">Nagoya University</a> and Shuzo Saito of <a href="/wiki/Nippon_Telegraph_and_Telephone" title="Nippon Telegraph and Telephone">Nippon Telegraph and Telephone</a> (NTT) in 1966. Further developments in LPC technology were made by <a href="/wiki/Bishnu_S._Atal" title="Bishnu S. Atal">Bishnu S. Atal</a> and <a href="/wiki/Manfred_R._Schroeder" title="Manfred R. Schroeder">Manfred R. Schroeder</a> at <a href="/wiki/Bell_Labs" title="Bell Labs">Bell Labs</a> during the 1970s.<sup id="cite_ref-13" class="reference"><a href="#cite_note-13"><span class="cite-bracket">[</span>13<span class="cite-bracket">]</span></a></sup> LPC was later the basis for early speech synthesizer chips, such as the <a href="/wiki/Texas_Instruments_LPC_Speech_Chips" title="Texas Instruments LPC Speech Chips">Texas Instruments LPC Speech Chips</a> used in the <a href="/wiki/Speak_%26_Spell_(toy)" title="Speak & Spell (toy)">Speak & Spell</a> toys from 1978. </p><p>In 1975, Fumitada Itakura developed the <a href="/wiki/Line_spectral_pairs" title="Line spectral pairs">line spectral pairs</a> (LSP) method for high-compression speech coding, while at NTT.<sup id="cite_ref-14" class="reference"><a href="#cite_note-14"><span class="cite-bracket">[</span>14<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-ieee_15-0" class="reference"><a href="#cite_note-ieee-15"><span class="cite-bracket">[</span>15<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-ItakuraHistory_16-0" class="reference"><a href="#cite_note-ItakuraHistory-16"><span class="cite-bracket">[</span>16<span class="cite-bracket">]</span></a></sup> From 1975 to 1981, Itakura studied problems in speech analysis and synthesis based on the LSP method.<sup id="cite_ref-ItakuraHistory_16-1" class="reference"><a href="#cite_note-ItakuraHistory-16"><span class="cite-bracket">[</span>16<span class="cite-bracket">]</span></a></sup> In 1980, his team developed an LSP-based speech synthesizer chip. LSP is an important technology for speech synthesis and coding, and in the 1990s was adopted by almost all international speech coding standards as an essential component, contributing to the enhancement of digital speech communication over mobile channels and the internet.<sup id="cite_ref-ieee_15-1" class="reference"><a href="#cite_note-ieee-15"><span class="cite-bracket">[</span>15<span class="cite-bracket">]</span></a></sup> </p><p>In 1975, <a href="/wiki/MUSA_(MUltichannel_Speaking_Automaton)" class="mw-redirect" title="MUSA (MUltichannel Speaking Automaton)">MUSA</a> was released, and was one of the first Speech Synthesis systems. It consisted of a stand-alone computer hardware and a specialized software that enabled it to read Italian. A second version, released in 1978, was also able to sing Italian in an "<a href="/wiki/A_cappella" title="A cappella">a cappella</a>" style.<sup id="cite_ref-17" class="reference"><a href="#cite_note-17"><span class="cite-bracket">[</span>17<span class="cite-bracket">]</span></a></sup> </p> <figure class="mw-default-size" typeof="mw:File/Thumb"><span><audio id="mwe_player_1" controls="" preload="none" data-mw-tmh="" class="mw-file-element" width="220" style="width:220px;" data-durationhint="15" data-mwtitle="DECtalk_demo.flac" data-mwprovider="wikimediacommons" resource="/wiki/File:DECtalk_demo.flac"><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/c/c7/DECtalk_demo.flac/DECtalk_demo.flac.ogg" type="audio/ogg; codecs="vorbis"" data-transcodekey="ogg" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/c/c7/DECtalk_demo.flac/DECtalk_demo.flac.mp3" type="audio/mpeg" data-transcodekey="mp3" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/c/c7/DECtalk_demo.flac" type="audio/flac" data-width="0" data-height="0" /><track src="https://commons.wikimedia.org/w/api.php?action=timedtext&title=File%3ADECtalk_demo.flac&lang=en&trackformat=vtt&origin=%2A" kind="subtitles" type="text/vtt" srclang="en" label="English ‪(en)‬" data-dir="ltr" /></audio></span><figcaption>DECtalk demo recording using the Perfect Paul and Uppity Ursula voices</figcaption></figure> <p>Dominant systems in the 1980s and 1990s were the <a href="/wiki/DECtalk" title="DECtalk">DECtalk</a> system, based largely on the work of <a href="/wiki/Dennis_H._Klatt" title="Dennis H. Klatt">Dennis Klatt</a> at MIT, and the Bell Labs system;<sup id="cite_ref-18" class="reference"><a href="#cite_note-18"><span class="cite-bracket">[</span>18<span class="cite-bracket">]</span></a></sup> the latter was one of the first multilingual language-independent systems, making extensive use of <a href="/wiki/Natural_language_processing" title="Natural language processing">natural language processing</a> methods. </p> <figure class="mw-halign-center" typeof="mw:File/Frameless"><a href="/wiki/File:DNC(Differentiable_Neural_Computer).png" class="mw-file-description"><img src="//upload.wikimedia.org/wikipedia/commons/thumb/1/1c/DNC%28Differentiable_Neural_Computer%29.png/600px-DNC%28Differentiable_Neural_Computer%29.png" decoding="async" width="600" height="308" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/1/1c/DNC%28Differentiable_Neural_Computer%29.png/900px-DNC%28Differentiable_Neural_Computer%29.png 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/1/1c/DNC%28Differentiable_Neural_Computer%29.png/1200px-DNC%28Differentiable_Neural_Computer%29.png 2x" data-file-width="1518" data-file-height="778" /></a><figcaption></figcaption></figure> <figure class="mw-default-size" typeof="mw:File/Thumb"><a href="/wiki/File:Fidelity_Chess_Challenger_Voice.jpg" class="mw-file-description"><img src="//upload.wikimedia.org/wikipedia/commons/thumb/0/06/Fidelity_Chess_Challenger_Voice.jpg/220px-Fidelity_Chess_Challenger_Voice.jpg" decoding="async" width="220" height="107" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/0/06/Fidelity_Chess_Challenger_Voice.jpg/330px-Fidelity_Chess_Challenger_Voice.jpg 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/0/06/Fidelity_Chess_Challenger_Voice.jpg/440px-Fidelity_Chess_Challenger_Voice.jpg 2x" data-file-width="1502" data-file-height="730" /></a><figcaption>Fidelity Voice Chess Challenger (1979), the first talking chess computer</figcaption></figure> <figure class="mw-default-size" typeof="mw:File/Thumb"><span><audio id="mwe_player_2" controls="" preload="none" data-mw-tmh="" class="mw-file-element" width="220" style="width:220px;" data-durationhint="28" data-mwtitle="Fidelity_Chess_Challenger_Voice_speech_output.flac" data-mwprovider="wikimediacommons" resource="/wiki/File:Fidelity_Chess_Challenger_Voice_speech_output.flac"><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/b/b6/Fidelity_Chess_Challenger_Voice_speech_output.flac/Fidelity_Chess_Challenger_Voice_speech_output.flac.ogg" type="audio/ogg; codecs="vorbis"" data-transcodekey="ogg" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/b/b6/Fidelity_Chess_Challenger_Voice_speech_output.flac/Fidelity_Chess_Challenger_Voice_speech_output.flac.mp3" type="audio/mpeg" data-transcodekey="mp3" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/b/b6/Fidelity_Chess_Challenger_Voice_speech_output.flac" type="audio/flac" data-width="0" data-height="0" /><track src="https://commons.wikimedia.org/w/api.php?action=timedtext&title=File%3AFidelity_Chess_Challenger_Voice_speech_output.flac&lang=en&trackformat=vtt&origin=%2A" kind="subtitles" type="text/vtt" srclang="en" label="English ‪(en)‬" data-dir="ltr" /></audio></span><figcaption>Speech output from Fidelity Voice Chess Challenger</figcaption></figure> <p><a href="/wiki/Handheld" class="mw-redirect" title="Handheld">Handheld</a> electronics featuring speech synthesis began emerging in the 1970s. One of the first was the <a href="/wiki/Telesensory_Systems" title="Telesensory Systems">Telesensory Systems Inc.</a> (TSI) <i>Speech+</i> portable calculator for the blind in 1976.<sup id="cite_ref-19" class="reference"><a href="#cite_note-19"><span class="cite-bracket">[</span>19<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-20" class="reference"><a href="#cite_note-20"><span class="cite-bracket">[</span>20<span class="cite-bracket">]</span></a></sup> Other devices had primarily educational purposes, such as the <a href="/wiki/Speak_%26_Spell_(toy)" title="Speak & Spell (toy)">Speak & Spell toy</a> produced by <a href="/wiki/Texas_Instruments" title="Texas Instruments">Texas Instruments</a> in 1978.<sup id="cite_ref-21" class="reference"><a href="#cite_note-21"><span class="cite-bracket">[</span>21<span class="cite-bracket">]</span></a></sup> Fidelity released a speaking version of its electronic chess computer in 1979.<sup id="cite_ref-22" class="reference"><a href="#cite_note-22"><span class="cite-bracket">[</span>22<span class="cite-bracket">]</span></a></sup> The first <a href="/wiki/Video_game" title="Video game">video game</a> to feature speech synthesis was the 1980 <a href="/wiki/Shoot_%27em_up" title="Shoot 'em up">shoot 'em up</a> <a href="/wiki/Arcade_game" title="Arcade game">arcade game</a>, <i><a href="/wiki/Stratovox" title="Stratovox">Stratovox</a></i> (known in Japan as <i>Speak & Rescue</i>), from <a href="/wiki/Sunsoft" class="mw-redirect" title="Sunsoft">Sun Electronics</a>.<sup id="cite_ref-23" class="reference"><a href="#cite_note-23"><span class="cite-bracket">[</span>23<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-24" class="reference"><a href="#cite_note-24"><span class="cite-bracket">[</span>24<span class="cite-bracket">]</span></a></sup> The first <a href="/wiki/Personal_computer_game" class="mw-redirect" title="Personal computer game">personal computer game</a> with speech synthesis was <i><a href="/wiki/Stealth_game#History" title="Stealth game">Manbiki Shoujo</a></i> (<i>Shoplifting Girl</i>), released in 1980 for the <a href="/wiki/PET_2001" class="mw-redirect" title="PET 2001">PET 2001</a>, for which the game's developer, Hiroshi Suzuki, developed a "<i>zero cross</i>" programming technique to produce a synthesized speech waveform.<sup id="cite_ref-25" class="reference"><a href="#cite_note-25"><span class="cite-bracket">[</span>25<span class="cite-bracket">]</span></a></sup> Another early example, the arcade version of <i><a href="/wiki/Berzerk_(video_game)" title="Berzerk (video game)">Berzerk</a></i>, also dates from 1980. The <a href="/wiki/Milton_Bradley_Company" title="Milton Bradley Company">Milton Bradley Company</a> produced the first multi-player <a href="/wiki/Electronic_game" title="Electronic game">electronic game</a> using voice synthesis, <i><a href="/wiki/Milton_(game)" title="Milton (game)">Milton</a></i>, in the same year. </p><p>In 1976, Computalker Consultants released their CT-1 Speech Synthesizer. Designed by D. Lloyd Rice and Jim Cooper, it was an analog synthesizer built to work with microcomputers using the S-100 bus standard.<sup id="cite_ref-26" class="reference"><a href="#cite_note-26"><span class="cite-bracket">[</span>26<span class="cite-bracket">]</span></a></sup> </p><p>Early electronic speech-synthesizers sounded robotic and were often barely intelligible. The quality of synthesized speech has steadily improved, but as of 2016<sup class="plainlinks noexcerpt noprint asof-tag update" style="display:none;"><a class="external text" href="https://en.wikipedia.org/w/index.php?title=Speech_synthesis&action=edit">[update]</a></sup> output from contemporary speech synthesis systems remains clearly distinguishable from actual human speech. </p><p>Synthesized voices typically sounded male until 1990, when <a href="/wiki/Ann_Syrdal" title="Ann Syrdal">Ann Syrdal</a>, at <a href="/wiki/AT%26T_Bell_Laboratories" class="mw-redirect" title="AT&T Bell Laboratories">AT&T Bell Laboratories</a>, created a female voice.<sup id="cite_ref-NewYorkTimes_27-0" class="reference"><a href="#cite_note-NewYorkTimes-27"><span class="cite-bracket">[</span>27<span class="cite-bracket">]</span></a></sup> </p><p>Kurzweil predicted in 2005 that as the <a href="/wiki/Cost-performance_ratio" class="mw-redirect" title="Cost-performance ratio">cost-performance ratio</a> caused speech synthesizers to become cheaper and more accessible, more people would benefit from the use of text-to-speech programs.<sup id="cite_ref-28" class="reference"><a href="#cite_note-28"><span class="cite-bracket">[</span>28<span class="cite-bracket">]</span></a></sup> </p> <div class="mw-heading mw-heading2"><h2 id="Synthesizer_technologies">Synthesizer technologies</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=3" title="Edit section: Synthesizer technologies"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>The most important qualities of a speech synthesis system are <i>naturalness</i> and <i><a href="/wiki/Intelligibility_(communication)" title="Intelligibility (communication)">intelligibility</a></i>.<b><sup id="cite_ref-29" class="reference"><a href="#cite_note-29"><span class="cite-bracket">[</span>29<span class="cite-bracket">]</span></a></sup></b> Naturalness describes how closely the output sounds like human speech, while intelligibility is the ease with which the output is understood. The ideal speech synthesizer is both natural and intelligible. Speech synthesis systems usually try to maximize both characteristics. </p><p>The two primary technologies generating synthetic speech waveforms are <i>concatenative synthesis</i> and <i><a href="/wiki/Formant" title="Formant">formant</a> synthesis</i>. Each technology has strengths and weaknesses, and the intended uses of a synthesis system will typically determine which approach is used. </p> <div class="mw-heading mw-heading3"><h3 id="Concatenation_synthesis">Concatenation synthesis</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=4" title="Edit section: Concatenation synthesis"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <style data-mw-deduplicate="TemplateStyles:r1236090951">.mw-parser-output .hatnote{font-style:italic}.mw-parser-output div.hatnote{padding-left:1.6em;margin-bottom:0.5em}.mw-parser-output .hatnote i{font-style:normal}.mw-parser-output .hatnote+link+.hatnote{margin-top:-0.5em}@media print{body.ns-0 .mw-parser-output .hatnote{display:none!important}}</style><div role="note" class="hatnote navigation-not-searchable">Main article: <a href="/wiki/Concatenative_synthesis" title="Concatenative synthesis">Concatenative synthesis</a></div> <p>Concatenative synthesis is based on the concatenation (stringing together) of segments of recorded speech. Generally, concatenative synthesis produces the most natural-sounding synthesized speech. However, differences between natural variations in speech and the nature of the automated techniques for segmenting the waveforms sometimes result in audible glitches in the output. There are three main sub-types of concatenative synthesis. </p> <div class="mw-heading mw-heading4"><h4 id="Unit_selection_synthesis">Unit selection synthesis</h4><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=5" title="Edit section: Unit selection synthesis"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>Unit selection synthesis uses large databases of recorded speech. During database creation, each recorded utterance is segmented into some or all of the following: individual <a href="/wiki/Phone_(phonetics)" title="Phone (phonetics)">phones</a>, <a href="/wiki/Diphone" title="Diphone">diphones</a>, half-phones, <a href="/wiki/Syllable" title="Syllable">syllables</a>, <a href="/wiki/Morpheme" title="Morpheme">morphemes</a>, <a href="/wiki/Word" title="Word">words</a>, <a href="/wiki/Phrase" title="Phrase">phrases</a>, and <a href="/wiki/Sentence_(linguistics)" title="Sentence (linguistics)">sentences</a>. Typically, the division into segments is done using a specially modified <a href="/wiki/Speech_recognition" title="Speech recognition">speech recognizer</a> set to a "forced alignment" mode with some manual correction afterward, using visual representations such as the <a href="/wiki/Waveform" title="Waveform">waveform</a> and <a href="/wiki/Spectrogram" title="Spectrogram">spectrogram</a>.<sup id="cite_ref-30" class="reference"><a href="#cite_note-30"><span class="cite-bracket">[</span>30<span class="cite-bracket">]</span></a></sup> An <a href="/wiki/Index_(database)" class="mw-redirect" title="Index (database)">index</a> of the units in the speech database is then created based on the segmentation and acoustic parameters like the <a href="/wiki/Fundamental_frequency" title="Fundamental frequency">fundamental frequency</a> (<a href="/wiki/Pitch_(music)" title="Pitch (music)">pitch</a>), duration, position in the syllable, and neighboring phones. At <a href="/wiki/Run_time_(program_lifecycle_phase)" class="mw-redirect" title="Run time (program lifecycle phase)">run time</a>, the desired target utterance is created by determining the best chain of candidate units from the database (unit selection). This process is typically achieved using a specially weighted <a href="/wiki/Decision_tree" title="Decision tree">decision tree</a>. </p><p>Unit selection provides the greatest naturalness, because it applies only a small amount of <a href="/wiki/Digital_signal_processing" title="Digital signal processing">digital signal processing</a> (DSP) to the recorded speech. DSP often makes recorded speech sound less natural, although some systems use a small amount of signal processing at the point of concatenation to smooth the waveform. The output from the best unit-selection systems is often indistinguishable from real human voices, especially in contexts for which the TTS system has been tuned. However, maximum naturalness typically require unit-selection speech databases to be very large, in some systems ranging into the <a href="/wiki/Gigabyte" title="Gigabyte">gigabytes</a> of recorded data, representing dozens of hours of speech.<sup id="cite_ref-31" class="reference"><a href="#cite_note-31"><span class="cite-bracket">[</span>31<span class="cite-bracket">]</span></a></sup> Also, unit selection algorithms have been known to select segments from a place that results in less than ideal synthesis (e.g. minor words become unclear) even when a better choice exists in the database.<sup id="cite_ref-32" class="reference"><a href="#cite_note-32"><span class="cite-bracket">[</span>32<span class="cite-bracket">]</span></a></sup> Recently, researchers have proposed various automated methods to detect unnatural segments in unit-selection speech synthesis systems.<sup id="cite_ref-33" class="reference"><a href="#cite_note-33"><span class="cite-bracket">[</span>33<span class="cite-bracket">]</span></a></sup> </p> <div class="mw-heading mw-heading4"><h4 id="Diphone_synthesis">Diphone synthesis</h4><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=6" title="Edit section: Diphone synthesis"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>Diphone synthesis uses a minimal speech database containing all the <a href="/wiki/Diphone" title="Diphone">diphones</a> (sound-to-sound transitions) occurring in a language. The number of diphones depends on the <a href="/wiki/Phonotactics" title="Phonotactics">phonotactics</a> of the language: for example, Spanish has about 800 diphones, and German about 2500. In diphone synthesis, only one example of each diphone is contained in the speech database. At runtime, the target <a href="/wiki/Prosody_(linguistics)" title="Prosody (linguistics)">prosody</a> of a sentence is superimposed on these minimal units by means of <a href="/wiki/Digital_signal_processing" title="Digital signal processing">digital signal processing</a> techniques such as <a href="/wiki/Linear_predictive_coding" title="Linear predictive coding">linear predictive coding</a>, <a href="/wiki/PSOLA" title="PSOLA">PSOLA</a><sup id="cite_ref-34" class="reference"><a href="#cite_note-34"><span class="cite-bracket">[</span>34<span class="cite-bracket">]</span></a></sup> or <a href="/wiki/MBROLA" title="MBROLA">MBROLA</a>.<sup id="cite_ref-35" class="reference"><a href="#cite_note-35"><span class="cite-bracket">[</span>35<span class="cite-bracket">]</span></a></sup> or more recent techniques such as pitch modification in the source domain using <a href="/wiki/Discrete_cosine_transform" title="Discrete cosine transform">discrete cosine transform</a>.<sup id="cite_ref-Muralishankar2004_36-0" class="reference"><a href="#cite_note-Muralishankar2004-36"><span class="cite-bracket">[</span>36<span class="cite-bracket">]</span></a></sup> Diphone synthesis suffers from the sonic glitches of concatenative synthesis and the robotic-sounding nature of formant synthesis, and has few of the advantages of either approach other than small size. As such, its use in commercial applications is declining,<sup class="noprint Inline-Template Template-Fact" style="white-space:nowrap;">[<i><a href="/wiki/Wikipedia:Citation_needed" title="Wikipedia:Citation needed"><span title="This claim needs references to reliable sources. (January 2012)">citation needed</span></a></i>]</sup> although it continues to be used in research because there are a number of freely available software implementations. An early example of Diphone synthesis is a teaching robot, <a href="/wiki/Leachim_(Robot)" title="Leachim (Robot)">Leachim</a>, that was invented by <a href="/wiki/Michael_J._Freeman" title="Michael J. Freeman">Michael J. Freeman</a>.<sup id="cite_ref-37" class="reference"><a href="#cite_note-37"><span class="cite-bracket">[</span>37<span class="cite-bracket">]</span></a></sup> Leachim contained information regarding class curricular and certain biographical information about the students whom it was programmed to teach.<sup id="cite_ref-38" class="reference"><a href="#cite_note-38"><span class="cite-bracket">[</span>38<span class="cite-bracket">]</span></a></sup> It was tested in a fourth grade classroom in <a href="/wiki/The_Bronx" title="The Bronx">the Bronx, New York</a>.<sup id="cite_ref-39" class="reference"><a href="#cite_note-39"><span class="cite-bracket">[</span>39<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-40" class="reference"><a href="#cite_note-40"><span class="cite-bracket">[</span>40<span class="cite-bracket">]</span></a></sup> </p> <div class="mw-heading mw-heading4"><h4 id="Domain-specific_synthesis">Domain-specific synthesis</h4><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=7" title="Edit section: Domain-specific synthesis"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>Domain-specific synthesis concatenates prerecorded words and phrases to create complete utterances. It is used in applications where the variety of texts the system will output is limited to a particular domain, like transit schedule announcements or weather reports.<sup id="cite_ref-41" class="reference"><a href="#cite_note-41"><span class="cite-bracket">[</span>41<span class="cite-bracket">]</span></a></sup> The technology is very simple to implement, and has been in commercial use for a long time, in devices like talking clocks and calculators. The level of naturalness of these systems can be very high because the variety of sentence types is limited, and they closely match the prosody and intonation of the original recordings.<sup class="noprint Inline-Template Template-Fact" style="white-space:nowrap;">[<i><a href="/wiki/Wikipedia:Citation_needed" title="Wikipedia:Citation needed"><span title="This claim needs references to reliable sources. (February 2007)">citation needed</span></a></i>]</sup> </p><p>Because these systems are limited by the words and phrases in their databases, they are not general-purpose and can only synthesize the combinations of words and phrases with which they have been preprogrammed. The blending of words within naturally spoken language however can still cause problems unless the many variations are taken into account. For example, in <a href="/wiki/Rhotic_and_non-rhotic_accents" class="mw-redirect" title="Rhotic and non-rhotic accents">non-rhotic</a> dialects of English the <i>"r"</i> in words like <i>"clear"</i> <span class="IPA nowrap" lang="und-Latn-fonipa" title="Representation in the International Phonetic Alphabet (IPA)">/ˈklɪə/</span> is usually only pronounced when the following word has a vowel as its first letter (e.g. <i>"clear out"</i> is realized as <span class="IPA nowrap" lang="und-Latn-fonipa" title="Representation in the International Phonetic Alphabet (IPA)">/ˌklɪəɹˈʌʊt/</span>). Likewise in <a href="/wiki/French_language" title="French language">French</a>, many final consonants become no longer silent if followed by a word that begins with a vowel, an effect called <a href="/wiki/Liaison_(French)" title="Liaison (French)">liaison</a>. This <a href="/wiki/Alternation_(linguistics)" title="Alternation (linguistics)">alternation</a> cannot be reproduced by a simple word-concatenation system, which would require additional complexity to be <a href="/wiki/Context-sensitive_grammar" title="Context-sensitive grammar">context-sensitive</a>. </p> <div class="mw-heading mw-heading3"><h3 id="Formant_synthesis">Formant synthesis</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=8" title="Edit section: Formant synthesis"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p><a href="/wiki/Formant" title="Formant">Formant</a> synthesis does not use human speech samples at runtime. Instead, the synthesized speech output is created using <a href="/wiki/Additive_synthesis" title="Additive synthesis">additive synthesis</a> and an acoustic model (<a href="/wiki/Physical_modelling_synthesis" title="Physical modelling synthesis">physical modelling synthesis</a>).<sup id="cite_ref-42" class="reference"><a href="#cite_note-42"><span class="cite-bracket">[</span>42<span class="cite-bracket">]</span></a></sup> Parameters such as <a href="/wiki/Fundamental_frequency" title="Fundamental frequency">fundamental frequency</a>, <a href="/wiki/Phonation" title="Phonation">voicing</a>, and <a href="/wiki/Noise" title="Noise">noise</a> levels are varied over time to create a <a href="/wiki/Waveform" title="Waveform">waveform</a> of artificial speech. This method is sometimes called <i>rules-based synthesis</i>; however, many concatenative systems also have rules-based components. Many systems based on formant synthesis technology generate artificial, robotic-sounding speech that would never be mistaken for human speech. However, maximum naturalness is not always the goal of a speech synthesis system, and formant synthesis systems have advantages over concatenative systems. Formant-synthesized speech can be reliably intelligible, even at very high speeds, avoiding the acoustic glitches that commonly plague concatenative systems. High-speed synthesized speech is used by the visually impaired to quickly navigate computers using a <a href="/wiki/Screen_reader" title="Screen reader">screen reader</a>. Formant synthesizers are usually smaller programs than concatenative systems because they do not have a database of speech samples. They can therefore be used in <a href="/wiki/Embedded_system" title="Embedded system">embedded systems</a>, where <a href="/wiki/Data_storage_device" class="mw-redirect" title="Data storage device">memory</a> and <a href="/wiki/Microprocessor" title="Microprocessor">microprocessor</a> power are especially limited. Because formant-based systems have complete control of all aspects of the output speech, a wide variety of prosodies and <a href="/wiki/Intonation_(linguistics)" title="Intonation (linguistics)">intonations</a> can be output, conveying not just questions and statements, but a variety of emotions and tones of voice. </p><p>Examples of non-real-time but highly accurate intonation control in formant synthesis include the work done in the late 1970s for the <a href="/wiki/Texas_Instruments" title="Texas Instruments">Texas Instruments</a> toy <a href="/wiki/Speak_%26_Spell_(game)" class="mw-redirect" title="Speak & Spell (game)">Speak & Spell</a>, and in the early 1980s <a href="/wiki/Sega" title="Sega">Sega</a> <a href="/wiki/Video_arcade" class="mw-redirect" title="Video arcade">arcade</a> machines<sup id="cite_ref-43" class="reference"><a href="#cite_note-43"><span class="cite-bracket">[</span>43<span class="cite-bracket">]</span></a></sup> and in many <a href="/wiki/Atari,_Inc." title="Atari, Inc.">Atari, Inc.</a> arcade games<sup id="cite_ref-44" class="reference"><a href="#cite_note-44"><span class="cite-bracket">[</span>44<span class="cite-bracket">]</span></a></sup> using the <a href="/wiki/Texas_Instruments_LPC_Speech_Chips" title="Texas Instruments LPC Speech Chips">TMS5220 LPC Chips</a>. Creating proper intonation for these projects was painstaking, and the results have yet to be matched by real-time text-to-speech interfaces.<sup id="cite_ref-45" class="reference"><a href="#cite_note-45"><span class="cite-bracket">[</span>45<span class="cite-bracket">]</span></a></sup> </p> <div class="mw-heading mw-heading3"><h3 id="Articulatory_synthesis">Articulatory synthesis</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=9" title="Edit section: Articulatory synthesis"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1236090951"><div role="note" class="hatnote navigation-not-searchable">Main article: <a href="/wiki/Articulatory_synthesis" title="Articulatory synthesis">Articulatory synthesis</a></div> <p>Articulatory synthesis consists of computational techniques for synthesizing speech based on models of the human <a href="/wiki/Vocal_tract" title="Vocal tract">vocal tract</a> and the articulation processes occurring there. The first articulatory synthesizer regularly used for laboratory experiments was developed at <a href="/wiki/Haskins_Laboratories" title="Haskins Laboratories">Haskins Laboratories</a> in the mid-1970s by <a href="/wiki/Philip_Rubin" title="Philip Rubin">Philip Rubin</a>, Tom Baer, and Paul Mermelstein. This synthesizer, known as ASY, was based on vocal tract models developed at <a href="/wiki/Bell_Laboratories" class="mw-redirect" title="Bell Laboratories">Bell Laboratories</a> in the 1960s and 1970s by Paul Mermelstein, Cecil Coker, and colleagues. </p><p>Until recently, articulatory synthesis models have not been incorporated into commercial speech synthesis systems. A notable exception is the <a href="/wiki/NeXT" title="NeXT">NeXT</a>-based system originally developed and marketed by Trillium Sound Research, a spin-off company of the <a href="/wiki/University_of_Calgary" title="University of Calgary">University of Calgary</a>, where much of the original research was conducted. Following the demise of the various incarnations of NeXT (started by <a href="/wiki/Steve_Jobs" title="Steve Jobs">Steve Jobs</a> in the late 1980s and merged with Apple Computer in 1997), the Trillium software was published under the GNU General Public License, with work continuing as <a href="/wiki/Gnuspeech" title="Gnuspeech">gnuspeech</a>. The system, first marketed in 1994, provides full articulatory-based text-to-speech conversion using a waveguide or transmission-line analog of the human oral and nasal tracts controlled by Carré's "distinctive region model". </p><p>More recent synthesizers, developed by Jorge C. Lucero and colleagues, incorporate models of vocal fold biomechanics, glottal aerodynamics and acoustic wave propagation in the bronchi, trachea, nasal and oral cavities, and thus constitute full systems of physics-based speech simulation.<sup id="cite_ref-:0_46-0" class="reference"><a href="#cite_note-:0-46"><span class="cite-bracket">[</span>46<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-:1_47-0" class="reference"><a href="#cite_note-:1-47"><span class="cite-bracket">[</span>47<span class="cite-bracket">]</span></a></sup> </p> <div class="mw-heading mw-heading3"><h3 id="HMM-based_synthesis">HMM-based synthesis</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=10" title="Edit section: HMM-based synthesis"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>HMM-based synthesis is a synthesis method based on <a href="/wiki/Hidden_Markov_model" title="Hidden Markov model">hidden Markov models</a>, also called Statistical Parametric Synthesis. In this system, the <a href="/wiki/Frequency_spectrum" class="mw-redirect" title="Frequency spectrum">frequency spectrum</a> (<a href="/wiki/Vocal_tract" title="Vocal tract">vocal tract</a>), <a href="/wiki/Fundamental_frequency" title="Fundamental frequency">fundamental frequency</a> (voice source), and duration (<a href="/wiki/Prosody_(linguistics)" title="Prosody (linguistics)">prosody</a>) of speech are modeled simultaneously by HMMs. Speech <a href="/wiki/Waveforms" class="mw-redirect" title="Waveforms">waveforms</a> are generated from HMMs themselves based on the <a href="/wiki/Maximum_likelihood" class="mw-redirect" title="Maximum likelihood">maximum likelihood</a> criterion.<sup id="cite_ref-48" class="reference"><a href="#cite_note-48"><span class="cite-bracket">[</span>48<span class="cite-bracket">]</span></a></sup> </p> <div class="mw-heading mw-heading3"><h3 id="Sinewave_synthesis">Sinewave synthesis</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=11" title="Edit section: Sinewave synthesis"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1236090951"><div role="note" class="hatnote navigation-not-searchable">Main article: <a href="/wiki/Sinewave_synthesis" title="Sinewave synthesis">Sinewave synthesis</a></div> <p>Sinewave synthesis is a technique for synthesizing speech by replacing the <a href="/wiki/Formants" class="mw-redirect" title="Formants">formants</a> (main bands of energy) with pure tone whistles.<sup id="cite_ref-49" class="reference"><a href="#cite_note-49"><span class="cite-bracket">[</span>49<span class="cite-bracket">]</span></a></sup> </p> <div class="mw-heading mw-heading3"><h3 id="Deep_learning-based_synthesis">Deep learning-based synthesis</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=12" title="Edit section: Deep learning-based synthesis"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1236090951"><div role="note" class="hatnote navigation-not-searchable">Main article: <a href="/wiki/Deep_learning_speech_synthesis" title="Deep learning speech synthesis">Deep learning speech synthesis</a></div> <figure class="mw-default-size" typeof="mw:File/Thumb"><span><audio id="mwe_player_3" controls="" preload="none" data-mw-tmh="" class="mw-file-element" width="220" style="width:220px;" data-durationhint="6" data-mwtitle="Larynx-HiFi-GAN_speech_sample.wav" data-mwprovider="wikimediacommons" resource="/wiki/File:Larynx-HiFi-GAN_speech_sample.wav"><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/f/f4/Larynx-HiFi-GAN_speech_sample.wav/Larynx-HiFi-GAN_speech_sample.wav.ogg" type="audio/ogg; codecs="vorbis"" data-transcodekey="ogg" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/f/f4/Larynx-HiFi-GAN_speech_sample.wav/Larynx-HiFi-GAN_speech_sample.wav.mp3" type="audio/mpeg" data-transcodekey="mp3" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/f/f4/Larynx-HiFi-GAN_speech_sample.wav" type="audio/wav" data-width="0" data-height="0" /><track src="https://commons.wikimedia.org/w/api.php?action=timedtext&title=File%3ALarynx-HiFi-GAN_speech_sample.wav&lang=en&trackformat=vtt&origin=%2A" kind="subtitles" type="text/vtt" srclang="en" label="English ‪(en)‬" data-dir="ltr" /></audio></span><figcaption>Speech synthesis example using the HiFi-GAN neural vocoder</figcaption></figure> <p>Deep learning speech synthesis uses <a href="/wiki/Deep_neural_network" class="mw-redirect" title="Deep neural network">deep neural networks</a> (DNN) to produce artificial speech from text (text-to-speech) or spectrum (vocoder). The deep neural networks are trained using a large amount of recorded speech and, in the case of a text-to-speech system, the associated labels and/or input text. </p><p><a href="/wiki/15.ai" title="15.ai">15.ai</a> uses a <i>multi-speaker model</i>—hundreds of voices are trained concurrently rather than sequentially, decreasing the required training time and enabling the model to learn and generalize shared emotional context, even for voices with no exposure to such emotional context.<sup id="cite_ref-arxivmello_50-0" class="reference"><a href="#cite_note-arxivmello-50"><span class="cite-bracket">[</span>50<span class="cite-bracket">]</span></a></sup> The <a href="/wiki/Deep_learning" title="Deep learning">deep learning</a> model used by the application is <a href="/wiki/Nondeterministic_algorithm" title="Nondeterministic algorithm">nondeterministic</a>: each time that speech is generated from the same string of text, the intonation of the speech will be slightly different. The application also supports manually altering the <a href="/wiki/Emotional_prosody" title="Emotional prosody">emotion</a> of a generated line using <i>emotional contextualizers</i> (a term coined by this project), a sentence or phrase that conveys the emotion of the take that serves as a guide for the model during inference.<sup id="cite_ref-automaton2_51-0" class="reference"><a href="#cite_note-automaton2-51"><span class="cite-bracket">[</span>51<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-Denfaminicogamer2_52-0" class="reference"><a href="#cite_note-Denfaminicogamer2-52"><span class="cite-bracket">[</span>52<span class="cite-bracket">]</span></a></sup> </p><p><a href="/wiki/ElevenLabs" title="ElevenLabs">ElevenLabs</a> is primarily known for its <a href="/wiki/Browser-based" class="mw-redirect" title="Browser-based">browser-based</a>, AI-assisted text-to-speech software, Speech Synthesis, which can produce lifelike speech by synthesizing <a href="/wiki/Vocal_emotion" class="mw-redirect" title="Vocal emotion">vocal emotion</a> and <a href="/wiki/Intonation_(linguistics)" title="Intonation (linguistics)">intonation</a>.<sup id="cite_ref-53" class="reference"><a href="#cite_note-53"><span class="cite-bracket">[</span>53<span class="cite-bracket">]</span></a></sup> The company states its software is built to adjust the intonation and pacing of delivery based on the context of language input used.<sup id="cite_ref-:13_54-0" class="reference"><a href="#cite_note-:13-54"><span class="cite-bracket">[</span>54<span class="cite-bracket">]</span></a></sup> It uses advanced algorithms to analyze the contextual aspects of text, aiming to detect emotions like anger, sadness, happiness, or alarm, which enables the system to understand the user's sentiment,<sup id="cite_ref-55" class="reference"><a href="#cite_note-55"><span class="cite-bracket">[</span>55<span class="cite-bracket">]</span></a></sup> resulting in a more realistic and human-like inflection. Other features include multilingual speech generation and long-form content creation with contextually-aware voices.<sup id="cite_ref-:34_56-0" class="reference"><a href="#cite_note-:34-56"><span class="cite-bracket">[</span>56<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-57" class="reference"><a href="#cite_note-57"><span class="cite-bracket">[</span>57<span class="cite-bracket">]</span></a></sup> </p><p>The DNN-based speech synthesizers are approaching the naturalness of the human voice. Examples of disadvantages of the method are low robustness when the data are not sufficient, lack of controllability and low performance in auto-regressive models. </p><p>For tonal languages, such as Chinese or Taiwanese language, there are different levels of <a href="/wiki/Tone_sandhi" title="Tone sandhi">tone sandhi</a> required and sometimes the output of speech synthesizer may result in the mistakes of tone sandhi.<sup id="cite_ref-58" class="reference"><a href="#cite_note-58"><span class="cite-bracket">[</span>58<span class="cite-bracket">]</span></a></sup> </p> <div class="mw-heading mw-heading3"><h3 id="Audio_deepfakes">Audio deepfakes</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=13" title="Edit section: Audio deepfakes"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <div class="excerpt-block"><style data-mw-deduplicate="TemplateStyles:r1066933788">.mw-parser-output .excerpt-hat .mw-editsection-like{font-style:normal}</style><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1236090951"><div role="note" class="hatnote navigation-not-searchable dablink excerpt-hat selfref">This section is an excerpt from <a href="/wiki/Audio_deepfake" title="Audio deepfake">Audio deepfake</a>.<span class="mw-editsection-like plainlinks"><span class="mw-editsection-bracket">[</span><a class="external text" href="https://en.wikipedia.org/w/index.php?title=Audio_deepfake&action=edit">edit</a><span class="mw-editsection-bracket">]</span></span></div><div class="excerpt"> <style data-mw-deduplicate="TemplateStyles:r1129693374">.mw-parser-output .hlist dl,.mw-parser-output .hlist ol,.mw-parser-output .hlist ul{margin:0;padding:0}.mw-parser-output .hlist dd,.mw-parser-output .hlist dt,.mw-parser-output .hlist li{margin:0;display:inline}.mw-parser-output .hlist.inline,.mw-parser-output .hlist.inline dl,.mw-parser-output .hlist.inline ol,.mw-parser-output .hlist.inline ul,.mw-parser-output .hlist dl dl,.mw-parser-output .hlist dl ol,.mw-parser-output .hlist dl ul,.mw-parser-output .hlist ol dl,.mw-parser-output .hlist ol ol,.mw-parser-output .hlist ol ul,.mw-parser-output .hlist ul dl,.mw-parser-output .hlist ul ol,.mw-parser-output .hlist ul ul{display:inline}.mw-parser-output .hlist .mw-empty-li{display:none}.mw-parser-output .hlist dt::after{content:": "}.mw-parser-output .hlist dd::after,.mw-parser-output .hlist li::after{content:" · ";font-weight:bold}.mw-parser-output .hlist dd:last-child::after,.mw-parser-output .hlist dt:last-child::after,.mw-parser-output .hlist li:last-child::after{content:none}.mw-parser-output .hlist dd dd:first-child::before,.mw-parser-output .hlist dd dt:first-child::before,.mw-parser-output .hlist dd li:first-child::before,.mw-parser-output .hlist dt dd:first-child::before,.mw-parser-output .hlist dt dt:first-child::before,.mw-parser-output .hlist dt li:first-child::before,.mw-parser-output .hlist li dd:first-child::before,.mw-parser-output .hlist li dt:first-child::before,.mw-parser-output .hlist li li:first-child::before{content:" (";font-weight:normal}.mw-parser-output .hlist dd dd:last-child::after,.mw-parser-output .hlist dd dt:last-child::after,.mw-parser-output .hlist dd li:last-child::after,.mw-parser-output .hlist dt dd:last-child::after,.mw-parser-output .hlist dt dt:last-child::after,.mw-parser-output .hlist dt li:last-child::after,.mw-parser-output .hlist li dd:last-child::after,.mw-parser-output .hlist li dt:last-child::after,.mw-parser-output .hlist li li:last-child::after{content:")";font-weight:normal}.mw-parser-output .hlist ol{counter-reset:listitem}.mw-parser-output .hlist ol>li{counter-increment:listitem}.mw-parser-output .hlist ol>li::before{content:" "counter(listitem)"\a0 "}.mw-parser-output .hlist dd ol>li:first-child::before,.mw-parser-output .hlist dt ol>li:first-child::before,.mw-parser-output .hlist li ol>li:first-child::before{content:" ("counter(listitem)"\a0 "}</style><style data-mw-deduplicate="TemplateStyles:r1246091330">.mw-parser-output .sidebar{width:22em;float:right;clear:right;margin:0.5em 0 1em 1em;background:var(--background-color-neutral-subtle,#f8f9fa);border:1px solid var(--border-color-base,#a2a9b1);padding:0.2em;text-align:center;line-height:1.4em;font-size:88%;border-collapse:collapse;display:table}body.skin-minerva .mw-parser-output .sidebar{display:table!important;float:right!important;margin:0.5em 0 1em 1em!important}.mw-parser-output .sidebar-subgroup{width:100%;margin:0;border-spacing:0}.mw-parser-output .sidebar-left{float:left;clear:left;margin:0.5em 1em 1em 0}.mw-parser-output .sidebar-none{float:none;clear:both;margin:0.5em 1em 1em 0}.mw-parser-output .sidebar-outer-title{padding:0 0.4em 0.2em;font-size:125%;line-height:1.2em;font-weight:bold}.mw-parser-output .sidebar-top-image{padding:0.4em}.mw-parser-output .sidebar-top-caption,.mw-parser-output .sidebar-pretitle-with-top-image,.mw-parser-output .sidebar-caption{padding:0.2em 0.4em 0;line-height:1.2em}.mw-parser-output .sidebar-pretitle{padding:0.4em 0.4em 0;line-height:1.2em}.mw-parser-output .sidebar-title,.mw-parser-output .sidebar-title-with-pretitle{padding:0.2em 0.8em;font-size:145%;line-height:1.2em}.mw-parser-output .sidebar-title-with-pretitle{padding:0.1em 0.4em}.mw-parser-output .sidebar-image{padding:0.2em 0.4em 0.4em}.mw-parser-output .sidebar-heading{padding:0.1em 0.4em}.mw-parser-output .sidebar-content{padding:0 0.5em 0.4em}.mw-parser-output .sidebar-content-with-subgroup{padding:0.1em 0.4em 0.2em}.mw-parser-output .sidebar-above,.mw-parser-output .sidebar-below{padding:0.3em 0.8em;font-weight:bold}.mw-parser-output .sidebar-collapse .sidebar-above,.mw-parser-output .sidebar-collapse .sidebar-below{border-top:1px solid #aaa;border-bottom:1px solid #aaa}.mw-parser-output .sidebar-navbar{text-align:right;font-size:115%;padding:0 0.4em 0.4em}.mw-parser-output .sidebar-list-title{padding:0 0.4em;text-align:left;font-weight:bold;line-height:1.6em;font-size:105%}.mw-parser-output .sidebar-list-title-c{padding:0 0.4em;text-align:center;margin:0 3.3em}@media(max-width:640px){body.mediawiki .mw-parser-output .sidebar{width:100%!important;clear:both;float:none!important;margin-left:0!important;margin-right:0!important}}body.skin--responsive .mw-parser-output .sidebar a>img{max-width:none!important}@media screen{html.skin-theme-clientpref-night .mw-parser-output .sidebar:not(.notheme) .sidebar-list-title,html.skin-theme-clientpref-night .mw-parser-output .sidebar:not(.notheme) .sidebar-title-with-pretitle{background:transparent!important}html.skin-theme-clientpref-night .mw-parser-output .sidebar:not(.notheme) .sidebar-title-with-pretitle a{color:var(--color-progressive)!important}}@media screen and (prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .sidebar:not(.notheme) .sidebar-list-title,html.skin-theme-clientpref-os .mw-parser-output .sidebar:not(.notheme) .sidebar-title-with-pretitle{background:transparent!important}html.skin-theme-clientpref-os .mw-parser-output .sidebar:not(.notheme) .sidebar-title-with-pretitle a{color:var(--color-progressive)!important}}@media print{body.ns-0 .mw-parser-output .sidebar{display:none!important}}</style><table class="sidebar sidebar-collapse nomobile nowraplinks hlist"><tbody><tr><td class="sidebar-pretitle">Part of a series on</td></tr><tr><th class="sidebar-title-with-pretitle"><a href="/wiki/Artificial_intelligence" title="Artificial intelligence">Artificial intelligence</a></th></tr><tr><td class="sidebar-image"><figure class="mw-halign-center" typeof="mw:File"><a href="/wiki/File:Dall-e_3_(jan_%2724)_artificial_intelligence_icon.png" class="mw-file-description"><img src="//upload.wikimedia.org/wikipedia/commons/thumb/6/64/Dall-e_3_%28jan_%2724%29_artificial_intelligence_icon.png/100px-Dall-e_3_%28jan_%2724%29_artificial_intelligence_icon.png" decoding="async" width="100" height="100" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/6/64/Dall-e_3_%28jan_%2724%29_artificial_intelligence_icon.png/150px-Dall-e_3_%28jan_%2724%29_artificial_intelligence_icon.png 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/6/64/Dall-e_3_%28jan_%2724%29_artificial_intelligence_icon.png/200px-Dall-e_3_%28jan_%2724%29_artificial_intelligence_icon.png 2x" data-file-width="820" data-file-height="820" /></a><figcaption></figcaption></figure></td></tr><tr><td class="sidebar-content"> <div class="sidebar-list mw-collapsible mw-collapsed"><div class="sidebar-list-title" style="text-align:center;color: var(--color-base)"><a href="/wiki/Artificial_intelligence#Goals" title="Artificial intelligence">Major goals</a></div><div class="sidebar-list-content mw-collapsible-content"> <ul><li><a href="/wiki/Artificial_general_intelligence" title="Artificial general intelligence">Artificial general intelligence</a></li> <li><a href="/wiki/Intelligent_agent" title="Intelligent agent">Intelligent agent</a></li> <li><a href="/wiki/Recursive_self-improvement" title="Recursive self-improvement">Recursive self-improvement</a></li> <li><a href="/wiki/Automated_planning_and_scheduling" title="Automated planning and scheduling">Planning</a></li> <li><a href="/wiki/Computer_vision" title="Computer vision">Computer vision</a></li> <li><a href="/wiki/General_game_playing" title="General game playing">General game playing</a></li> <li><a href="/wiki/Knowledge_representation_and_reasoning" title="Knowledge representation and reasoning">Knowledge reasoning</a></li> <li><a href="/wiki/Natural_language_processing" title="Natural language processing">Natural language processing</a></li> <li><a href="/wiki/Robotics" title="Robotics">Robotics</a></li> <li><a href="/wiki/AI_safety" title="AI safety">AI safety</a></li></ul></div></div></td> </tr><tr><td class="sidebar-content"> <div class="sidebar-list mw-collapsible mw-collapsed"><div class="sidebar-list-title" style="text-align:center;color: var(--color-base)">Approaches</div><div class="sidebar-list-content mw-collapsible-content"> <ul><li><a href="/wiki/Machine_learning" title="Machine learning">Machine learning</a></li> <li><a href="/wiki/Symbolic_artificial_intelligence" title="Symbolic artificial intelligence">Symbolic</a></li> <li><a href="/wiki/Deep_learning" title="Deep learning">Deep learning</a></li> <li><a href="/wiki/Bayesian_network" title="Bayesian network">Bayesian networks</a></li> <li><a href="/wiki/Evolutionary_algorithm" title="Evolutionary algorithm">Evolutionary algorithms</a></li> <li><a href="/wiki/Hybrid_intelligent_system" title="Hybrid intelligent system">Hybrid intelligent systems</a></li> <li><a href="/wiki/Artificial_intelligence_systems_integration" title="Artificial intelligence systems integration">Systems integration</a></li></ul></div></div></td> </tr><tr><td class="sidebar-content"> <div class="sidebar-list mw-collapsible mw-collapsed"><div class="sidebar-list-title" style="text-align:center;color: var(--color-base)"><a href="/wiki/Applications_of_artificial_intelligence" title="Applications of artificial intelligence">Applications</a></div><div class="sidebar-list-content mw-collapsible-content"> <ul><li><a href="/wiki/Machine_learning_in_bioinformatics" title="Machine learning in bioinformatics">Bioinformatics</a></li> <li><a href="/wiki/Deepfake" title="Deepfake">Deepfake</a></li> <li><a href="/wiki/Machine_learning_in_earth_sciences" title="Machine learning in earth sciences">Earth sciences</a></li> <li><a href="/wiki/Applications_of_artificial_intelligence#Finance" title="Applications of artificial intelligence"> Finance </a></li> <li><a href="/wiki/Generative_artificial_intelligence" title="Generative artificial intelligence">Generative AI</a> <ul><li><a href="/wiki/Artificial_intelligence_art" title="Artificial intelligence art">Art</a></li> <li><a href="/wiki/Generative_audio" title="Generative audio">Audio</a></li> <li><a href="/wiki/Music_and_artificial_intelligence" title="Music and artificial intelligence">Music</a></li></ul></li> <li><a href="/wiki/Artificial_intelligence_in_government" title="Artificial intelligence in government">Government</a></li> <li><a href="/wiki/Artificial_intelligence_in_healthcare" title="Artificial intelligence in healthcare">Healthcare</a> <ul><li><a href="/wiki/Artificial_intelligence_in_mental_health" title="Artificial intelligence in mental health">Mental health</a></li></ul></li> <li><a href="/wiki/Artificial_intelligence_in_industry" title="Artificial intelligence in industry">Industry</a></li> <li><a href="/wiki/Machine_translation" title="Machine translation">Translation</a></li> <li><a href="/wiki/Artificial_intelligence_arms_race" title="Artificial intelligence arms race"> Military </a></li> <li><a href="/wiki/Machine_learning_in_physics" title="Machine learning in physics">Physics</a></li> <li><a href="/wiki/List_of_artificial_intelligence_projects" title="List of artificial intelligence projects">Projects</a></li></ul></div></div></td> </tr><tr><td class="sidebar-content"> <div class="sidebar-list mw-collapsible mw-collapsed"><div class="sidebar-list-title" style="text-align:center;color: var(--color-base)"><a href="/wiki/Philosophy_of_artificial_intelligence" title="Philosophy of artificial intelligence">Philosophy</a></div><div class="sidebar-list-content mw-collapsible-content"> <ul><li><a href="/wiki/Artificial_consciousness" title="Artificial consciousness">Artificial consciousness</a></li> <li><a href="/wiki/Chinese_room" title="Chinese room">Chinese room</a></li> <li><a href="/wiki/Friendly_artificial_intelligence" title="Friendly artificial intelligence">Friendly AI</a></li> <li><a href="/wiki/AI_control_problem" class="mw-redirect" title="AI control problem">Control problem</a>/<a href="/wiki/AI_takeover" title="AI takeover">Takeover</a></li> <li><a href="/wiki/Ethics_of_artificial_intelligence" title="Ethics of artificial intelligence">Ethics</a></li> <li><a href="/wiki/Existential_risk_from_artificial_general_intelligence" class="mw-redirect" title="Existential risk from artificial general intelligence">Existential risk</a></li> <li><a href="/wiki/Regulation_of_artificial_intelligence" title="Regulation of artificial intelligence">Regulation</a></li> <li><a href="/wiki/Turing_test" title="Turing test">Turing test</a></li></ul></div></div></td> </tr><tr><td class="sidebar-content"> <div class="sidebar-list mw-collapsible mw-collapsed"><div class="sidebar-list-title" style="text-align:center;color: var(--color-base)"><a href="/wiki/History_of_artificial_intelligence" title="History of artificial intelligence">History</a></div><div class="sidebar-list-content mw-collapsible-content"> <ul><li><a href="/wiki/Timeline_of_artificial_intelligence" title="Timeline of artificial intelligence">Timeline</a></li> <li><a href="/wiki/Progress_in_artificial_intelligence" title="Progress in artificial intelligence">Progress</a></li> <li><a href="/wiki/AI_winter" title="AI winter">AI winter</a></li> <li><a href="/wiki/AI_boom" title="AI boom">AI boom</a></li></ul></div></div></td> </tr><tr><td class="sidebar-content"> <div class="sidebar-list mw-collapsible mw-collapsed"><div class="sidebar-list-title" style="text-align:center;color: var(--color-base)">Glossary</div><div class="sidebar-list-content mw-collapsible-content"> <ul><li><a href="/wiki/Glossary_of_artificial_intelligence" title="Glossary of artificial intelligence">Glossary</a></li></ul></div></div></td> </tr><tr><td class="sidebar-navbar"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1129693374"><style data-mw-deduplicate="TemplateStyles:r1239400231">.mw-parser-output .navbar{display:inline;font-size:88%;font-weight:normal}.mw-parser-output .navbar-collapse{float:left;text-align:left}.mw-parser-output .navbar-boxtext{word-spacing:0}.mw-parser-output .navbar ul{display:inline-block;white-space:nowrap;line-height:inherit}.mw-parser-output .navbar-brackets::before{margin-right:-0.125em;content:"[ "}.mw-parser-output .navbar-brackets::after{margin-left:-0.125em;content:" ]"}.mw-parser-output .navbar li{word-spacing:-0.125em}.mw-parser-output .navbar a>span,.mw-parser-output .navbar a>abbr{text-decoration:inherit}.mw-parser-output .navbar-mini abbr{font-variant:small-caps;border-bottom:none;text-decoration:none;cursor:inherit}.mw-parser-output .navbar-ct-full{font-size:114%;margin:0 7em}.mw-parser-output .navbar-ct-mini{font-size:114%;margin:0 4em}html.skin-theme-clientpref-night .mw-parser-output .navbar li a abbr{color:var(--color-base)!important}@media(prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .navbar li a abbr{color:var(--color-base)!important}}@media print{.mw-parser-output .navbar{display:none!important}}</style><div class="navbar plainlinks hlist navbar-mini"><ul><li class="nv-view"><a href="/wiki/Template:Artificial_intelligence" title="Template:Artificial intelligence"><abbr title="View this template">v</abbr></a></li><li class="nv-talk"><a href="/wiki/Template_talk:Artificial_intelligence" title="Template talk:Artificial intelligence"><abbr title="Discuss this template">t</abbr></a></li><li class="nv-edit"><a href="/wiki/Special:EditPage/Template:Artificial_intelligence" title="Special:EditPage/Template:Artificial intelligence"><abbr title="Edit this template">e</abbr></a></li></ul></div></td></tr></tbody></table> Audio <a href="/wiki/Deepfake" title="Deepfake">deepfake</a> technology, also referred to as voice cloning or deepfake audio, is an application of <a href="/wiki/Artificial_intelligence" title="Artificial intelligence">artificial intelligence</a> designed to generate <a href="/wiki/Speech" title="Speech">speech</a> that convincingly mimics specific individuals, often synthesizing phrases or sentences they have never spoken.<sup id="cite_ref-59" class="reference"><a href="#cite_note-59"><span class="cite-bracket">[</span>59<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-60" class="reference"><a href="#cite_note-60"><span class="cite-bracket">[</span>60<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-Audio_deepfake_:0_61-0" class="reference"><a href="#cite_note-Audio_deepfake_:0-61"><span class="cite-bracket">[</span>61<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-62" class="reference"><a href="#cite_note-62"><span class="cite-bracket">[</span>62<span class="cite-bracket">]</span></a></sup> Initially developed with the intent to enhance various aspects of human life, it has practical applications such as generating <a href="/wiki/Audiobooks" class="mw-redirect" title="Audiobooks">audiobooks</a> and assisting individuals who have <a href="/wiki/Aphasia" title="Aphasia">lost their voices due to medical conditions</a>.<sup id="cite_ref-Audio_deepfake_:10_63-0" class="reference"><a href="#cite_note-Audio_deepfake_:10-63"><span class="cite-bracket">[</span>63<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-Audio_deepfake_:11_64-0" class="reference"><a href="#cite_note-Audio_deepfake_:11-64"><span class="cite-bracket">[</span>64<span class="cite-bracket">]</span></a></sup> Additionally, it has commercial uses, including the creation of personalized <a href="/wiki/Embodied_agent" title="Embodied agent">digital assistants</a>, natural-sounding <a href="/wiki/Text-to-speech" class="mw-redirect" title="Text-to-speech">text-to-speech</a> systems, and advanced speech <a href="/wiki/Translation_services" class="mw-redirect" title="Translation services">translation services</a>.<sup id="cite_ref-65" class="reference"><a href="#cite_note-65"><span class="cite-bracket">[</span>65<span class="cite-bracket">]</span></a></sup></div></div><p>In 2023, <a href="/wiki/Vice_Media" title="Vice Media">VICE</a> reporter <a href="/w/index.php?title=Joseph_Cox_(journalist)&action=edit&redlink=1" class="new" title="Joseph Cox (journalist) (page does not exist)">Joseph Cox</a> published findings that he had recorded five minutes of himself talking and then used a tool developed by ElevenLabs to create voice deepfakes that defeated a bank's <a href="/wiki/Speaker_recognition" title="Speaker recognition">voice-authentication</a> system.<sup id="cite_ref-66" class="reference"><a href="#cite_note-66"><span class="cite-bracket">[</span>66<span class="cite-bracket">]</span></a></sup> </p><div class="mw-heading mw-heading2"><h2 id="Challenges">Challenges</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=14" title="Edit section: Challenges"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <div class="mw-heading mw-heading3"><h3 id="Text_normalization_challenges">Text normalization challenges</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=15" title="Edit section: Text normalization challenges"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>The process of normalizing text is rarely straightforward. Texts are full of <a href="/wiki/Heteronym_(linguistics)" title="Heteronym (linguistics)">heteronyms</a>, <a href="/wiki/Number" title="Number">numbers</a>, and <a href="/wiki/Abbreviation" title="Abbreviation">abbreviations</a> that all require expansion into a phonetic representation. There are many spellings in English which are pronounced differently based on context. For example, "My latest project is to learn how to better project my voice" contains two pronunciations of "project". </p><p>Most text-to-speech (TTS) systems do not generate <a href="/wiki/Semantics#Linguistics" title="Semantics">semantic</a> representations of their input texts, as processes for doing so are unreliable, poorly understood, and computationally ineffective. As a result, various <a href="/wiki/Heuristic" title="Heuristic">heuristic</a> techniques are used to guess the proper way to disambiguate <a href="/wiki/Homograph" title="Homograph">homographs</a>, like examining neighboring words and using statistics about frequency of occurrence. </p><p>Recently TTS systems have begun to use HMMs (discussed <a class="mw-selflink-fragment" href="#HMM-based_synthesis">above</a>) to generate "<a href="/wiki/Part-of-speech_tagging" title="Part-of-speech tagging">parts of speech</a>" to aid in disambiguating homographs. This technique is quite successful for many cases such as whether "read" should be pronounced as "red" implying past tense, or as "reed" implying present tense. Typical error rates when using HMMs in this fashion are usually below five percent. These techniques also work well for most European languages, although access to required training <a href="/wiki/Text_corpus" title="Text corpus">corpora</a> is frequently difficult in these languages. </p><p>Deciding how to convert numbers is another problem that TTS systems have to address. It is a simple programming challenge to convert a number into words (at least in English), like "1325" becoming "one thousand three hundred twenty-five". However, numbers occur in many different contexts; "1325" may also be read as "one three two five", "thirteen twenty-five" or "thirteen hundred and twenty five". A TTS system can often infer how to expand a number based on surrounding words, numbers, and punctuation, and sometimes the system provides a way to specify the context if it is ambiguous.<sup id="cite_ref-67" class="reference"><a href="#cite_note-67"><span class="cite-bracket">[</span>67<span class="cite-bracket">]</span></a></sup> Roman numerals can also be read differently depending on context. For example, "Henry VIII" reads as "Henry the Eighth", while "Chapter VIII" reads as "Chapter Eight". </p><p>Similarly, abbreviations can be ambiguous. For example, the abbreviation "in" for "inches" must be differentiated from the word "in", and the address "12 St John St." uses the same abbreviation for both "Saint" and "Street". TTS systems with intelligent front ends can make educated guesses about ambiguous abbreviations, while others provide the same result in all cases, resulting in nonsensical (and sometimes comical) outputs, such as "<a href="/wiki/Ulysses_S._Grant" title="Ulysses S. Grant">Ulysses S. Grant</a>" being rendered as "Ulysses South Grant". </p> <div class="mw-heading mw-heading3"><h3 id="Text-to-phoneme_challenges">Text-to-phoneme challenges</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=16" title="Edit section: Text-to-phoneme challenges"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <style data-mw-deduplicate="TemplateStyles:r1251242444">.mw-parser-output .ambox{border:1px solid #a2a9b1;border-left:10px solid #36c;background-color:#fbfbfb;box-sizing:border-box}.mw-parser-output .ambox+link+.ambox,.mw-parser-output .ambox+link+style+.ambox,.mw-parser-output .ambox+link+link+.ambox,.mw-parser-output .ambox+.mw-empty-elt+link+.ambox,.mw-parser-output .ambox+.mw-empty-elt+link+style+.ambox,.mw-parser-output .ambox+.mw-empty-elt+link+link+.ambox{margin-top:-1px}html body.mediawiki .mw-parser-output .ambox.mbox-small-left{margin:4px 1em 4px 0;overflow:hidden;width:238px;border-collapse:collapse;font-size:88%;line-height:1.25em}.mw-parser-output .ambox-speedy{border-left:10px solid #b32424;background-color:#fee7e6}.mw-parser-output .ambox-delete{border-left:10px solid #b32424}.mw-parser-output .ambox-content{border-left:10px solid #f28500}.mw-parser-output .ambox-style{border-left:10px solid #fc3}.mw-parser-output .ambox-move{border-left:10px solid #9932cc}.mw-parser-output .ambox-protection{border-left:10px solid #a2a9b1}.mw-parser-output .ambox .mbox-text{border:none;padding:0.25em 0.5em;width:100%}.mw-parser-output .ambox .mbox-image{border:none;padding:2px 0 2px 0.5em;text-align:center}.mw-parser-output .ambox .mbox-imageright{border:none;padding:2px 0.5em 2px 0;text-align:center}.mw-parser-output .ambox .mbox-empty-cell{border:none;padding:0;width:1px}.mw-parser-output .ambox .mbox-image-div{width:52px}@media(min-width:720px){.mw-parser-output .ambox{margin:0 10%}}@media print{body.ns-0 .mw-parser-output .ambox{display:none!important}}</style><table class="box-Unreferenced_section plainlinks metadata ambox ambox-content ambox-Unreferenced" role="presentation"><tbody><tr><td class="mbox-image"><div class="mbox-image-div"><span typeof="mw:File"><a href="/wiki/File:Question_book-new.svg" class="mw-file-description"><img alt="" src="//upload.wikimedia.org/wikipedia/en/thumb/9/99/Question_book-new.svg/50px-Question_book-new.svg.png" decoding="async" width="50" height="39" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/en/thumb/9/99/Question_book-new.svg/75px-Question_book-new.svg.png 1.5x, //upload.wikimedia.org/wikipedia/en/thumb/9/99/Question_book-new.svg/100px-Question_book-new.svg.png 2x" data-file-width="512" data-file-height="399" /></a></span></div></td><td class="mbox-text"><div class="mbox-text-span">This section <b>does not <a href="/wiki/Wikipedia:Citing_sources" title="Wikipedia:Citing sources">cite</a> any <a href="/wiki/Wikipedia:Verifiability" title="Wikipedia:Verifiability">sources</a></b>.<span class="hide-when-compact"> Please help <a href="/wiki/Special:EditPage/Speech_synthesis" title="Special:EditPage/Speech synthesis">improve this section</a> by <a href="/wiki/Help:Referencing_for_beginners" title="Help:Referencing for beginners">adding citations to reliable sources</a>. Unsourced material may be challenged and <a href="/wiki/Wikipedia:Verifiability#Burden_of_evidence" title="Wikipedia:Verifiability">removed</a>.</span> <span class="date-container"><i>(<span class="date">April 2023</span>)</i></span><span class="hide-when-compact"><i> (<small><a href="/wiki/Help:Maintenance_template_removal" title="Help:Maintenance template removal">Learn how and when to remove this message</a></small>)</i></span></div></td></tr></tbody></table> <p>Speech synthesis systems use two basic approaches to determine the pronunciation of a word based on its <a href="/wiki/Spelling" title="Spelling">spelling</a>, a process which is often called text-to-phoneme or <a href="/wiki/Grapheme" title="Grapheme">grapheme</a>-to-phoneme conversion (<a href="/wiki/Phoneme" title="Phoneme">phoneme</a> is the term used by <a href="/wiki/Linguistics" title="Linguistics">linguists</a> to describe distinctive sounds in a <a href="/wiki/Language" title="Language">language</a>). The simplest approach to text-to-phoneme conversion is the dictionary-based approach, where a large dictionary containing all the words of a language and their correct <a href="/wiki/Pronunciation" title="Pronunciation">pronunciations</a> is stored by the program. Determining the correct pronunciation of each word is a matter of looking up each word in the dictionary and replacing the spelling with the pronunciation specified in the dictionary. The other approach is rule-based, in which pronunciation rules are applied to words to determine their pronunciations based on their spellings. This is similar to the "sounding out", or <a href="/wiki/Synthetic_phonics" title="Synthetic phonics">synthetic phonics</a>, approach to learning reading. </p><p>Each approach has advantages and drawbacks. The dictionary-based approach is quick and accurate, but completely fails if it is given a word which is not in its dictionary. As dictionary size grows, so too does the memory space requirements of the synthesis system. On the other hand, the rule-based approach works on any input, but the complexity of the rules grows substantially as the system takes into account irregular spellings or pronunciations. (Consider that the word "of" is very common in English, yet is the only word in which the letter "f" is pronounced <span class="IPA nowrap" lang="und-Latn-fonipa" title="Representation in the International Phonetic Alphabet (IPA)">[v]</span>.) As a result, nearly all speech synthesis systems use a combination of these approaches. </p><p>Languages with a <a href="/wiki/Phonemic_orthography" title="Phonemic orthography">phonemic orthography</a> have a very regular writing system, and the prediction of the pronunciation of words based on their spellings is quite successful. Speech synthesis systems for such languages often use the rule-based method extensively, resorting to dictionaries only for those few words, like foreign names and loanwords, whose pronunciations are not obvious from their spellings. On the other hand, speech synthesis systems for languages like English, which have extremely irregular spelling systems, are more likely to rely on dictionaries, and to use rule-based methods only for unusual words, or words that are not in their dictionaries. </p> <div class="mw-heading mw-heading3"><h3 id="Evaluation_challenges">Evaluation challenges</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=17" title="Edit section: Evaluation challenges"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>The consistent evaluation of speech synthesis systems may be difficult because of a lack of universally agreed objective evaluation criteria. Different organizations often use different speech data. The quality of speech synthesis systems also depends on the quality of the production technique (which may involve analogue or digital recording) and on the facilities used to replay the speech. Evaluating speech synthesis systems has therefore often been compromised by differences between production techniques and replay facilities. </p><p>Since 2005, however, some researchers have started to evaluate speech synthesis systems using a common speech dataset.<sup id="cite_ref-68" class="reference"><a href="#cite_note-68"><span class="cite-bracket">[</span>68<span class="cite-bracket">]</span></a></sup> </p> <div class="mw-heading mw-heading3"><h3 id="Prosodics_and_emotional_content">Prosodics and emotional content</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=18" title="Edit section: Prosodics and emotional content"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1236090951"><div role="note" class="hatnote navigation-not-searchable">See also: <a href="/wiki/Emotional_speech_recognition" class="mw-redirect" title="Emotional speech recognition">Emotional speech recognition</a> and <a href="/wiki/Prosody_(linguistics)" title="Prosody (linguistics)">Prosody (linguistics)</a></div> <p>A study in the journal <i>Speech Communication</i> by Amy Drahota and colleagues at the <a href="/wiki/University_of_Portsmouth" title="University of Portsmouth">University of Portsmouth</a>, <a href="/wiki/UK" class="mw-redirect" title="UK">UK</a>, reported that listeners to voice recordings could determine, at better than chance levels, whether or not the speaker was smiling.<sup id="cite_ref-69" class="reference"><a href="#cite_note-69"><span class="cite-bracket">[</span>69<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-70" class="reference"><a href="#cite_note-70"><span class="cite-bracket">[</span>70<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-71" class="reference"><a href="#cite_note-71"><span class="cite-bracket">[</span>71<span class="cite-bracket">]</span></a></sup> It was suggested that identification of the vocal features that signal emotional content may be used to help make synthesized speech sound more natural. One of the related issues is modification of the <a href="/wiki/Pitch_contour" title="Pitch contour">pitch contour</a> of the sentence, depending upon whether it is an affirmative, interrogative or exclamatory sentence. One of the techniques for pitch modification<sup id="cite_ref-Muralishankar2004_36-1" class="reference"><a href="#cite_note-Muralishankar2004-36"><span class="cite-bracket">[</span>36<span class="cite-bracket">]</span></a></sup> uses <a href="/wiki/Discrete_cosine_transform" title="Discrete cosine transform">discrete cosine transform</a> in the source domain (<a href="/wiki/Linear_prediction" title="Linear prediction">linear prediction</a> residual). Such pitch synchronous pitch modification techniques need a priori pitch marking of the synthesis speech database using techniques such as epoch extraction using dynamic <a href="/wiki/Plosive" title="Plosive">plosion</a> index applied on the integrated linear prediction residual of the <a href="/wiki/Voice_(phonetics)" title="Voice (phonetics)">voiced</a> regions of speech.<sup id="cite_ref-72" class="reference"><a href="#cite_note-72"><span class="cite-bracket">[</span>72<span class="cite-bracket">]</span></a></sup> In general, prosody remains a challenge for speech synthesizers, and is an active research topic. </p> <div class="mw-heading mw-heading2"><h2 id="Dedicated_hardware">Dedicated hardware</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=19" title="Edit section: Dedicated hardware"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <figure class="mw-default-size" typeof="mw:File/Thumb"><a href="/wiki/File:Electronic_Vowel_Synthesizer,_Bell_System_Science_Experiment_No.3.jpg" class="mw-file-description"><img src="//upload.wikimedia.org/wikipedia/commons/thumb/d/d5/Electronic_Vowel_Synthesizer%2C_Bell_System_Science_Experiment_No.3.jpg/220px-Electronic_Vowel_Synthesizer%2C_Bell_System_Science_Experiment_No.3.jpg" decoding="async" width="220" height="165" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/d/d5/Electronic_Vowel_Synthesizer%2C_Bell_System_Science_Experiment_No.3.jpg/330px-Electronic_Vowel_Synthesizer%2C_Bell_System_Science_Experiment_No.3.jpg 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/d/d5/Electronic_Vowel_Synthesizer%2C_Bell_System_Science_Experiment_No.3.jpg/440px-Electronic_Vowel_Synthesizer%2C_Bell_System_Science_Experiment_No.3.jpg 2x" data-file-width="800" data-file-height="600" /></a><figcaption>A speech synthesis kit produced by Bell System</figcaption></figure> <ul><li><a href="/wiki/Icophone" title="Icophone">Icophone</a></li> <li><a href="/wiki/General_Instrument_SP0256-AL2" class="mw-redirect" title="General Instrument SP0256-AL2">General Instrument SP0256-AL2</a></li> <li><a href="/wiki/National_Semiconductor" title="National Semiconductor">National Semiconductor</a> DT1050 Digitalker (Mozer – <a href="/wiki/Forrest_Mozer" class="mw-redirect" title="Forrest Mozer">Forrest Mozer</a>)</li> <li><a href="/wiki/Texas_Instruments_LPC_Speech_Chips" title="Texas Instruments LPC Speech Chips">Texas Instruments LPC Speech Chips</a><sup id="cite_ref-TI_will_exit_dedicated_speech-synthesis_chips,_transfer_products_to_Sensory_73-0" class="reference"><a href="#cite_note-TI_will_exit_dedicated_speech-synthesis_chips,_transfer_products_to_Sensory-73"><span class="cite-bracket">[</span>73<span class="cite-bracket">]</span></a></sup></li></ul> <div class="mw-heading mw-heading2"><h2 id="Hardware_and_software_systems">Hardware and software systems</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=20" title="Edit section: Hardware and software systems"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>Popular systems offering speech synthesis as a built-in capability. </p> <div class="mw-heading mw-heading3"><h3 id="Texas_Instruments">Texas Instruments</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=21" title="Edit section: Texas Instruments"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1236090951"><div role="note" class="hatnote navigation-not-searchable">Main article: <a href="/wiki/Texas_Instruments_LPC_Speech_Chips" title="Texas Instruments LPC Speech Chips">Texas Instruments LPC Speech Chips</a></div> <figure class="mw-default-size" typeof="mw:File/Thumb"><span><audio id="mwe_player_4" controls="" preload="none" data-mw-tmh="" class="mw-file-element" width="220" style="width:220px;" data-durationhint="4" data-mwtitle="Texas_Instruments_TI-99_4A_speech_demo.flac" data-mwprovider="wikimediacommons" resource="/wiki/File:Texas_Instruments_TI-99_4A_speech_demo.flac"><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/4/44/Texas_Instruments_TI-99_4A_speech_demo.flac/Texas_Instruments_TI-99_4A_speech_demo.flac.ogg" type="audio/ogg; codecs="vorbis"" data-transcodekey="ogg" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/4/44/Texas_Instruments_TI-99_4A_speech_demo.flac/Texas_Instruments_TI-99_4A_speech_demo.flac.mp3" type="audio/mpeg" data-transcodekey="mp3" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/4/44/Texas_Instruments_TI-99_4A_speech_demo.flac" type="audio/flac" data-width="0" data-height="0" /><track src="https://commons.wikimedia.org/w/api.php?action=timedtext&title=File%3ATexas_Instruments_TI-99_4A_speech_demo.flac&lang=en&trackformat=vtt&origin=%2A" kind="subtitles" type="text/vtt" srclang="en" label="English ‪(en)‬" data-dir="ltr" /></audio></span><figcaption>TI-99/4A speech demo using the built-in vocabulary</figcaption></figure> <p>In the early 1980s, TI was known as a pioneer in speech synthesis, and a highly popular plug-in speech synthesizer module was available for the TI-99/4 and 4A. Speech synthesizers were offered free with the purchase of a number of cartridges and were used by many TI-written video games (games offered with speech during this promotion included <i><a href="/wiki/Alpiner_(video_game)" title="Alpiner (video game)">Alpiner</a></i> and <i><a href="/wiki/Parsec_(video_game)" title="Parsec (video game)">Parsec</a></i>). The synthesizer uses a variant of linear predictive coding and has a small in-built vocabulary. The original intent was to release small cartridges that plugged directly into the synthesizer unit, which would increase the device's built-in vocabulary. However, the success of software text-to-speech in the Terminal Emulator II cartridge canceled that plan. </p> <div class="mw-heading mw-heading3"><h3 id="Mattel">Mattel</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=22" title="Edit section: Mattel"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>The <a href="/wiki/Mattel" title="Mattel">Mattel</a> <a href="/wiki/Intellivision" title="Intellivision">Intellivision</a> game console offered the <a href="/wiki/Intellivoice" title="Intellivoice">Intellivoice</a> Voice Synthesis module in 1982. It included the <a href="/wiki/General_Instrument_SP0256" title="General Instrument SP0256">SP0256 Narrator</a> speech synthesizer chip on a removable cartridge. The Narrator had 2kB of Read-Only Memory (ROM), and this was utilized to store a database of generic words that could be combined to make phrases in Intellivision games. Since the Orator chip could also accept speech data from external memory, any additional words or phrases needed could be stored inside the cartridge itself. The data consisted of strings of analog-filter coefficients to modify the behavior of the chip's synthetic vocal-tract model, rather than simple digitized samples. </p> <div class="mw-heading mw-heading3"><h3 id="SAM">SAM</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=23" title="Edit section: SAM"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <figure class="mw-default-size" typeof="mw:File/Thumb"><span><audio id="mwe_player_5" controls="" preload="none" data-mw-tmh="" class="mw-file-element" width="220" style="width:220px;" data-durationhint="18" data-mwtitle="C64_Software_Automatic_Mouth_demo.flac" data-mwprovider="wikimediacommons" resource="/wiki/File:C64_Software_Automatic_Mouth_demo.flac"><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/a/af/C64_Software_Automatic_Mouth_demo.flac/C64_Software_Automatic_Mouth_demo.flac.ogg" type="audio/ogg; codecs="vorbis"" data-transcodekey="ogg" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/a/af/C64_Software_Automatic_Mouth_demo.flac/C64_Software_Automatic_Mouth_demo.flac.mp3" type="audio/mpeg" data-transcodekey="mp3" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/a/af/C64_Software_Automatic_Mouth_demo.flac" type="audio/flac" data-width="0" data-height="0" /><track src="https://commons.wikimedia.org/w/api.php?action=timedtext&title=File%3AC64_Software_Automatic_Mouth_demo.flac&lang=en&trackformat=vtt&origin=%2A" kind="subtitles" type="text/vtt" srclang="en" label="English ‪(en)‬" data-dir="ltr" /></audio></span><figcaption>A demo of SAM on the C64</figcaption></figure> <p>Also released in 1982, <a href="/wiki/Software_Automatic_Mouth" title="Software Automatic Mouth">Software Automatic Mouth</a> was the first commercial all-software voice synthesis program. It was later used as the basis for <a href="/wiki/Macintalk" class="mw-redirect" title="Macintalk">Macintalk</a>. The program was available for non-Macintosh Apple computers (including the Apple II, and the Lisa), various Atari models and the Commodore 64. The Apple version preferred additional hardware that contained DACs, although it could instead use the computer's one-bit audio output (with the addition of much distortion) if the card was not present. The Atari made use of the embedded POKEY audio chip. Speech playback on the Atari normally disabled interrupt requests and shut down the ANTIC chip during vocal output. The audible output is extremely distorted speech when the screen is on. The Commodore 64 made use of the 64's embedded SID audio chip. </p> <div class="mw-heading mw-heading3"><h3 id="Atari">Atari</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=24" title="Edit section: Atari"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <figure class="mw-default-size" typeof="mw:File/Thumb"><span><audio id="mwe_player_6" controls="" preload="none" data-mw-tmh="" class="mw-file-element" width="220" style="width:220px;" data-durationhint="12" data-mwtitle="Atari_ST_speech_synthesis_demo.flac" data-mwprovider="wikimediacommons" resource="/wiki/File:Atari_ST_speech_synthesis_demo.flac"><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/0/07/Atari_ST_speech_synthesis_demo.flac/Atari_ST_speech_synthesis_demo.flac.ogg" type="audio/ogg; codecs="vorbis"" data-transcodekey="ogg" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/0/07/Atari_ST_speech_synthesis_demo.flac/Atari_ST_speech_synthesis_demo.flac.mp3" type="audio/mpeg" data-transcodekey="mp3" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/0/07/Atari_ST_speech_synthesis_demo.flac" type="audio/flac" data-width="0" data-height="0" /><track src="https://commons.wikimedia.org/w/api.php?action=timedtext&title=File%3AAtari_ST_speech_synthesis_demo.flac&lang=en&trackformat=vtt&origin=%2A" kind="subtitles" type="text/vtt" srclang="en" label="English ‪(en)‬" data-dir="ltr" /></audio></span><figcaption>Atari ST speech synthesis demo</figcaption></figure> <p>Arguably, the first speech system integrated into an <a href="/wiki/Operating_system" title="Operating system">operating system</a> was the circa 1983 unreleased Atari <a href="/wiki/Atari_8-bit_computers#Unreleased_XL_models" title="Atari 8-bit computers">1400XL/1450XL</a> computers. These used the Votrax SC01 chip and a <a href="/wiki/Finite_state_machine" class="mw-redirect" title="Finite state machine">finite state machine</a> to enable World English Spelling text-to-speech synthesis.<sup id="cite_ref-74" class="reference"><a href="#cite_note-74"><span class="cite-bracket">[</span>74<span class="cite-bracket">]</span></a></sup> </p><p>The <a href="/wiki/Atari_ST" title="Atari ST">Atari ST</a> computers were sold with "stspeech.tos" on floppy disk. </p> <div class="mw-heading mw-heading3"><h3 id="Apple">Apple</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=25" title="Edit section: Apple"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <figure class="mw-default-size" typeof="mw:File/Thumb"><span><audio id="mwe_player_7" controls="" preload="none" data-mw-tmh="" class="mw-file-element" width="220" style="width:220px;" data-durationhint="15" data-mwtitle="MacinTalk_1_demo.flac" data-mwprovider="wikimediacommons" resource="/wiki/File:MacinTalk_1_demo.flac"><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/8/86/MacinTalk_1_demo.flac/MacinTalk_1_demo.flac.ogg" type="audio/ogg; codecs="vorbis"" data-transcodekey="ogg" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/8/86/MacinTalk_1_demo.flac/MacinTalk_1_demo.flac.mp3" type="audio/mpeg" data-transcodekey="mp3" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/8/86/MacinTalk_1_demo.flac" type="audio/flac" data-width="0" data-height="0" /><track src="https://commons.wikimedia.org/w/api.php?action=timedtext&title=File%3AMacinTalk_1_demo.flac&lang=en&trackformat=vtt&origin=%2A" kind="subtitles" type="text/vtt" srclang="en" label="English ‪(en)‬" data-dir="ltr" /></audio></span><figcaption>MacinTalk 1 demo</figcaption></figure> <figure class="mw-default-size" typeof="mw:File/Thumb"><span><audio id="mwe_player_8" controls="" preload="none" data-mw-tmh="" class="mw-file-element" width="220" style="width:220px;" data-durationhint="9" data-mwtitle="MacinTalk_2_demo.flac" data-mwprovider="wikimediacommons" resource="/wiki/File:MacinTalk_2_demo.flac"><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/0/03/MacinTalk_2_demo.flac/MacinTalk_2_demo.flac.ogg" type="audio/ogg; codecs="vorbis"" data-transcodekey="ogg" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/0/03/MacinTalk_2_demo.flac/MacinTalk_2_demo.flac.mp3" type="audio/mpeg" data-transcodekey="mp3" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/0/03/MacinTalk_2_demo.flac" type="audio/flac" data-width="0" data-height="0" /><track src="https://commons.wikimedia.org/w/api.php?action=timedtext&title=File%3AMacinTalk_2_demo.flac&lang=en&trackformat=vtt&origin=%2A" kind="subtitles" type="text/vtt" srclang="en" label="English ‪(en)‬" data-dir="ltr" /></audio></span><figcaption>MacinTalk 2 demo featuring the Mr. Hughes and Marvin voices</figcaption></figure> <p>The first speech system integrated into an <a href="/wiki/Operating_system" title="Operating system">operating system</a> that shipped in quantity was <a href="/wiki/Apple_Computer" class="mw-redirect" title="Apple Computer">Apple Computer</a>'s <a href="/wiki/PlainTalk#Original_MacInTalk" title="PlainTalk">MacInTalk</a>. The software was licensed from third-party developers Joseph Katz and Mark Barton (later, SoftVoice, Inc.) and was featured during the 1984 introduction of the Macintosh computer. This January demo required 512 kilobytes of RAM memory. As a result, it could not run in the 128 kilobytes of RAM the first Mac actually shipped with.<sup id="cite_ref-demo_75-0" class="reference"><a href="#cite_note-demo-75"><span class="cite-bracket">[</span>75<span class="cite-bracket">]</span></a></sup> So, the demo was accomplished with a prototype 512k Mac, although those in attendance were not told of this and the synthesis demo created considerable excitement for the Macintosh. In the early 1990s Apple expanded its capabilities offering system wide text-to-speech support. With the introduction of faster PowerPC-based computers they included higher quality voice sampling. Apple also introduced <a href="/wiki/Speech_recognition" title="Speech recognition">speech recognition</a> into its systems which provided a fluid command set. More recently, Apple has added sample-based voices. Starting as a curiosity, the speech system of Apple <a href="/wiki/Macintosh" class="mw-redirect" title="Macintosh">Macintosh</a> has evolved into a fully supported program, <a href="/wiki/PlainTalk" title="PlainTalk">PlainTalk</a>, for people with vision problems. <a href="/wiki/VoiceOver" title="VoiceOver">VoiceOver</a> was for the first time featured in 2005 in <a href="/wiki/Mac_OS_X_Tiger" title="Mac OS X Tiger">Mac OS X Tiger</a> (10.4). During 10.4 (Tiger) and first releases of 10.5 (<a href="/wiki/Mac_OS_X_Leopard" title="Mac OS X Leopard">Leopard</a>) there was only one standard voice shipping with Mac OS X. Starting with 10.6 (<a href="/wiki/Mac_OS_X_Snow_Leopard" title="Mac OS X Snow Leopard">Snow Leopard</a>), the user can choose out of a wide range list of multiple voices. VoiceOver voices feature the taking of realistic-sounding breaths between sentences, as well as improved clarity at high read rates over PlainTalk. Mac OS X also includes <a href="/w/index.php?title=Say_(software)&action=edit&redlink=1" class="new" title="Say (software) (page does not exist)">say</a>, a <a href="/wiki/Command-line_interface" title="Command-line interface">command-line based</a> application that converts text to audible speech. The <a href="/wiki/AppleScript" title="AppleScript">AppleScript</a> Standard Additions includes a say verb that allows a script to use any of the installed voices and to control the pitch, speaking rate and modulation of the spoken text. </p> <div class="mw-heading mw-heading3"><h3 id="Amazon">Amazon</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=26" title="Edit section: Amazon"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>Used in <a href="/wiki/Amazon_Alexa" title="Amazon Alexa">Alexa</a> and as <a href="/wiki/Software_as_a_service" title="Software as a service">Software as a Service</a> in AWS<sup id="cite_ref-76" class="reference"><a href="#cite_note-76"><span class="cite-bracket">[</span>76<span class="cite-bracket">]</span></a></sup> (from 2017). </p> <div class="mw-heading mw-heading3"><h3 id="AmigaOS">AmigaOS</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=27" title="Edit section: AmigaOS"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <figure class="mw-default-size" typeof="mw:File/Thumb"><span><audio id="mwe_player_9" controls="" preload="none" data-mw-tmh="" class="mw-file-element" width="220" style="width:220px;" data-durationhint="12" data-mwtitle="Amiga_speech_synthesis.flac" data-mwprovider="wikimediacommons" resource="/wiki/File:Amiga_speech_synthesis.flac"><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/f/f6/Amiga_speech_synthesis.flac/Amiga_speech_synthesis.flac.ogg" type="audio/ogg; codecs="vorbis"" data-transcodekey="ogg" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/f/f6/Amiga_speech_synthesis.flac/Amiga_speech_synthesis.flac.mp3" type="audio/mpeg" data-transcodekey="mp3" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/f/f6/Amiga_speech_synthesis.flac" type="audio/flac" data-width="0" data-height="0" /><track src="https://commons.wikimedia.org/w/api.php?action=timedtext&title=File%3AAmiga_speech_synthesis.flac&lang=en&trackformat=vtt&origin=%2A" kind="subtitles" type="text/vtt" srclang="en" label="English ‪(en)‬" data-dir="ltr" /></audio></span><figcaption>Example of speech synthesis with the included Say utility in Workbench 1.3</figcaption></figure> <figure class="mw-default-size mw-halign-right" typeof="mw:File"><a href="/wiki/File:SoftVoice.svg" class="mw-file-description"><img src="//upload.wikimedia.org/wikipedia/commons/thumb/6/6f/SoftVoice.svg/158px-SoftVoice.svg.png" decoding="async" width="158" height="336" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/6/6f/SoftVoice.svg/237px-SoftVoice.svg.png 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/6/6f/SoftVoice.svg/316px-SoftVoice.svg.png 2x" data-file-width="158" data-file-height="336" /></a><figcaption></figcaption></figure> <p>The second operating system to feature advanced speech synthesis capabilities was <a href="/wiki/AmigaOS" title="AmigaOS">AmigaOS</a>, introduced in 1985. The voice synthesis was licensed by <a href="/wiki/Commodore_International" title="Commodore International">Commodore International</a> from SoftVoice, Inc., who also developed the original <a href="/wiki/MacinTalk" class="mw-redirect" title="MacinTalk">MacinTalk</a> text-to-speech system. It featured a complete system of voice emulation for American English, with both male and female voices and "stress" indicator markers, made possible through the <a href="/wiki/Amiga" title="Amiga">Amiga</a>'s audio <a href="/wiki/Chipset" title="Chipset">chipset</a>.<sup id="cite_ref-77" class="reference"><a href="#cite_note-77"><span class="cite-bracket">[</span>77<span class="cite-bracket">]</span></a></sup> The synthesis system was divided into a translator library which converted unrestricted English text into a standard set of phonetic codes and a narrator device which implemented a formant model of speech generation.. AmigaOS also featured a high-level "<a href="/wiki/AmigaOS#Speech_synthesis" title="AmigaOS">Speak Handler</a>", which allowed command-line users to redirect text output to speech. Speech synthesis was occasionally used in third-party programs, particularly word processors and educational software. The synthesis software remained largely unchanged from the first AmigaOS release and Commodore eventually removed speech synthesis support from AmigaOS 2.1 onward. </p><p>Despite the American English phoneme limitation, an unofficial version with multilingual speech synthesis was developed. This made use of an enhanced version of the translator library which could translate a number of languages, given a set of rules for each language.<sup id="cite_ref-78" class="reference"><a href="#cite_note-78"><span class="cite-bracket">[</span>78<span class="cite-bracket">]</span></a></sup> </p> <div class="mw-heading mw-heading3"><h3 id="Microsoft_Windows">Microsoft Windows</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=28" title="Edit section: Microsoft Windows"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1236090951"><div role="note" class="hatnote navigation-not-searchable">See also: <a href="/wiki/Microsoft_Agent" title="Microsoft Agent">Microsoft Agent</a></div> <p>Modern <a href="/wiki/Microsoft_Windows" title="Microsoft Windows">Windows</a> desktop systems can use <a href="/wiki/Speech_Application_Programming_Interface#SAPI_1-4_API_family" class="mw-redirect" title="Speech Application Programming Interface">SAPI 4</a> and <a href="/wiki/Speech_Application_Programming_Interface#SAPI_5_API_family" class="mw-redirect" title="Speech Application Programming Interface">SAPI 5</a> components to support speech synthesis and <a href="/wiki/Speech_recognition" title="Speech recognition">speech recognition</a>. SAPI 4.0 was available as an optional add-on for <a href="/wiki/Windows_95" title="Windows 95">Windows 95</a> and <a href="/wiki/Windows_98" title="Windows 98">Windows 98</a>. <a href="/wiki/Windows_2000" title="Windows 2000">Windows 2000</a> added <a href="/wiki/Microsoft_Narrator" class="mw-redirect" title="Microsoft Narrator">Narrator</a>, a text-to-speech utility for people who have visual impairment. Third-party programs such as JAWS for Windows, Window-Eyes, Non-visual Desktop Access, Supernova and System Access can perform various text-to-speech tasks such as reading text aloud from a specified website, email account, text document, the Windows clipboard, the user's keyboard typing, etc. Not all programs can use speech synthesis directly.<sup id="cite_ref-Narrator_79-0" class="reference"><a href="#cite_note-Narrator-79"><span class="cite-bracket">[</span>79<span class="cite-bracket">]</span></a></sup> Some programs can use plug-ins, extensions or add-ons to read text aloud. Third-party programs are available that can read text from the system clipboard. </p><p><a href="/wiki/Microsoft_Speech_Server" title="Microsoft Speech Server">Microsoft Speech Server</a> is a server-based package for voice synthesis and recognition. It is designed for network use with <a href="/wiki/Web_applications" class="mw-redirect" title="Web applications">web applications</a> and <a href="/wiki/Call_centers" class="mw-redirect" title="Call centers">call centers</a>. </p> <div class="mw-heading mw-heading3"><h3 id="Votrax">Votrax</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=29" title="Edit section: Votrax"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1236090951"><div role="note" class="hatnote navigation-not-searchable">Main article: <a href="/wiki/Votrax" title="Votrax">Votrax</a></div> <figure class="mw-default-size" typeof="mw:File/Thumb"><span><audio id="mwe_player_10" controls="" preload="none" data-mw-tmh="" class="mw-file-element" width="220" style="width:220px;" data-durationhint="14" data-mwtitle="Votrax_speech_synthesizer_demo.flac" data-mwprovider="wikimediacommons" resource="/wiki/File:Votrax_speech_synthesizer_demo.flac"><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/0/08/Votrax_speech_synthesizer_demo.flac/Votrax_speech_synthesizer_demo.flac.ogg" type="audio/ogg; codecs="vorbis"" data-transcodekey="ogg" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/transcoded/0/08/Votrax_speech_synthesizer_demo.flac/Votrax_speech_synthesizer_demo.flac.mp3" type="audio/mpeg" data-transcodekey="mp3" data-width="0" data-height="0" /><source src="//upload.wikimedia.org/wikipedia/commons/0/08/Votrax_speech_synthesizer_demo.flac" type="audio/flac" data-width="0" data-height="0" /><track src="https://commons.wikimedia.org/w/api.php?action=timedtext&title=File%3AVotrax_speech_synthesizer_demo.flac&lang=en&trackformat=vtt&origin=%2A" kind="subtitles" type="text/vtt" srclang="en" label="English ‪(en)‬" data-dir="ltr" /></audio></span><figcaption>Votrax Type 'N Talk speech synthesizer (1980)</figcaption></figure> <p>From 1971 to 1996, Votrax produced a number of commercial speech synthesizer components. A Votrax synthesizer was included in the first generation Kurzweil Reading Machine for the Blind. </p> <div class="mw-heading mw-heading2"><h2 id="Text-to-speech_systems">Text-to-speech systems</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=30" title="Edit section: Text-to-speech systems"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>Text-to-speech (TTS) refers to the ability of computers to read text aloud. A TTS engine converts written text to a phonemic representation, then converts the phonemic representation to waveforms that can be output as sound. TTS engines with different languages, dialects and specialized vocabularies are available through third-party publishers.<sup id="cite_ref-microsoft.com_80-0" class="reference"><a href="#cite_note-microsoft.com-80"><span class="cite-bracket">[</span>80<span class="cite-bracket">]</span></a></sup> </p> <div class="mw-heading mw-heading3"><h3 id="Android">Android</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=31" title="Edit section: Android"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>Version 1.6 of <a href="/wiki/Android_(operating_system)" title="Android (operating system)">Android</a> added support for speech synthesis (TTS).<sup id="cite_ref-81" class="reference"><a href="#cite_note-81"><span class="cite-bracket">[</span>81<span class="cite-bracket">]</span></a></sup> </p> <div class="mw-heading mw-heading3"><h3 id="Internet">Internet</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=32" title="Edit section: Internet"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>Currently, there are a number of <a href="/wiki/Application_software" title="Application software">applications</a>, <a href="/wiki/Plug-in_(computing)" title="Plug-in (computing)">plugins</a> and gadgets that can read messages directly from an <a href="/wiki/E-mail_client" class="mw-redirect" title="E-mail client">e-mail client</a> and web pages from a <a href="/wiki/Web_browser" title="Web browser">web browser</a> or <a href="/wiki/Google_Toolbar" title="Google Toolbar">Google Toolbar</a>. Some specialized software can narrate <a href="/wiki/RSS" title="RSS">RSS-feeds</a>. On one hand, online RSS-narrators simplify information delivery by allowing users to listen to their favourite news sources and to convert them to <a href="/wiki/Podcast" title="Podcast">podcasts</a>. On the other hand, on-line RSS-readers are available on almost any personal computer connected to the Internet. Users can download generated audio files to portable devices, e.g. with a help of <a href="/wiki/Podcast" title="Podcast">podcast</a> receiver, and listen to them while walking, jogging or commuting to work. </p><p>A growing field in Internet based TTS is web-based <a href="/wiki/Assistive_technology" title="Assistive technology">assistive technology</a>, e.g. 'Browsealoud' from a UK company and <a href="/wiki/Readspeaker" class="mw-redirect" title="Readspeaker">Readspeaker</a>. It can deliver TTS functionality to anyone (for reasons of accessibility, convenience, entertainment or information) with access to a web browser. The non-profit project <a href="/wiki/Wikipedia:WikiProject_Spoken_Wikipedia/Pediaphon" title="Wikipedia:WikiProject Spoken Wikipedia/Pediaphon">Pediaphon</a> was created in 2006 to provide a similar web-based TTS interface to the Wikipedia.<sup id="cite_ref-82" class="reference"><a href="#cite_note-82"><span class="cite-bracket">[</span>82<span class="cite-bracket">]</span></a></sup> </p><p>Other work is being done in the context of the <a href="/wiki/W3C" class="mw-redirect" title="W3C">W3C</a> through the W3C Audio Incubator Group with the involvement of The BBC and Google Inc. </p> <div class="mw-heading mw-heading3"><h3 id="Open_source">Open source</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=33" title="Edit section: Open source"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>Some <a href="/wiki/Open-source_software" title="Open-source software">open-source software</a> systems are available, such as: </p> <ul><li><a href="/wiki/ESpeak" title="ESpeak">eSpeak</a> which supports a broad range of languages.</li> <li><a href="/wiki/Festival_Speech_Synthesis_System" title="Festival Speech Synthesis System">Festival Speech Synthesis System</a> which uses diphone-based synthesis, as well as more modern and better-sounding techniques.</li> <li><a href="/wiki/Gnuspeech" title="Gnuspeech">gnuspeech</a> which uses articulatory synthesis<sup id="cite_ref-83" class="reference"><a href="#cite_note-83"><span class="cite-bracket">[</span>83<span class="cite-bracket">]</span></a></sup> from the <a href="/wiki/Free_Software_Foundation" title="Free Software Foundation">Free Software Foundation</a>.</li></ul> <div class="mw-heading mw-heading3"><h3 id="Others">Others</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=34" title="Edit section: Others"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <ul><li>Following the commercial failure of the hardware-based Intellivoice, gaming developers sparingly used software synthesis in later games<sup class="noprint Inline-Template Template-Fact" style="white-space:nowrap;">[<i><a href="/wiki/Wikipedia:Citation_needed" title="Wikipedia:Citation needed"><span title="This claim needs references to reliable sources. (April 2020)">citation needed</span></a></i>]</sup>. Earlier systems from Atari, such as the <a href="/wiki/Atari_5200" title="Atari 5200">Atari 5200</a> (Baseball) and the <a href="/wiki/Atari_2600" title="Atari 2600">Atari 2600</a> (<a href="/wiki/Quadrun" title="Quadrun">Quadrun</a> and Open Sesame), also had games utilizing software synthesis.<sup class="noprint Inline-Template Template-Fact" style="white-space:nowrap;">[<i><a href="/wiki/Wikipedia:Citation_needed" title="Wikipedia:Citation needed"><span title="This claim needs references to reliable sources. (April 2020)">citation needed</span></a></i>]</sup></li> <li>Some <a href="/wiki/E-book_readers" class="mw-redirect" title="E-book readers">e-book readers</a>, such as the <a href="/wiki/Amazon_Kindle" title="Amazon Kindle">Amazon Kindle</a>, <a href="/wiki/Samsung" title="Samsung">Samsung</a> E6, <a href="/wiki/PocketBook_eReader" class="mw-redirect" title="PocketBook eReader">PocketBook eReader</a> Pro, <a href="/wiki/EnTourage_eDGe" title="EnTourage eDGe">enTourage eDGe</a>, and the Bebook Neo.</li> <li>The <a href="/wiki/BBC_Micro" title="BBC Micro">BBC Micro</a> incorporated the Texas Instruments TMS5220 speech synthesis chip.</li> <li>Some models of Texas Instruments home computers produced in 1979 and 1981 (<a href="/wiki/TI-99/4A" title="TI-99/4A">Texas Instruments TI-99/4 and TI-99/4A</a>) were capable of text-to-phoneme synthesis or reciting complete words and phrases (text-to-dictionary), using a very popular Speech Synthesizer peripheral. TI used a proprietary <a href="/wiki/Codec" title="Codec">codec</a> to embed complete spoken phrases into applications, primarily video games.<sup id="cite_ref-84" class="reference"><a href="#cite_note-84"><span class="cite-bracket">[</span>84<span class="cite-bracket">]</span></a></sup></li> <li><a href="/wiki/IBM" title="IBM">IBM</a>'s <a href="/wiki/OS/2_Warp" class="mw-redirect" title="OS/2 Warp">OS/2 Warp 4</a> included VoiceType, a precursor to <a href="/wiki/IBM_ViaVoice" title="IBM ViaVoice">IBM ViaVoice</a>.</li> <li><a href="/wiki/Global_Positioning_System" title="Global Positioning System">GPS</a> Navigation units produced by <a href="/wiki/Garmin" title="Garmin">Garmin</a>, <a href="/wiki/Magellan_Navigation" title="Magellan Navigation">Magellan</a>, <a href="/wiki/TomTom" title="TomTom">TomTom</a> and others use speech synthesis for automobile navigation.</li> <li><a href="/wiki/Yamaha_Corporation" title="Yamaha Corporation">Yamaha</a> produced a music synthesizer in 1999, the <a href="/wiki/Yamaha_FS1R" title="Yamaha FS1R">Yamaha FS1R</a> which included a Formant synthesis capability. Sequences of up to 512 individual vowel and consonant formants could be stored and replayed, allowing short vocal phrases to be synthesized.</li></ul> <div class="mw-heading mw-heading3"><h3 id="Digital_sound-alikes">Digital sound-alikes</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=35" title="Edit section: Digital sound-alikes"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>At the 2018 <a href="/wiki/Conference_on_Neural_Information_Processing_Systems" title="Conference on Neural Information Processing Systems">Conference on Neural Information Processing Systems</a> (NeurIPS) researchers from <a href="/wiki/Google" title="Google">Google</a> presented the work 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis', which <a href="/wiki/Transfer_learning" title="Transfer learning">transfers learning</a> from <a href="/wiki/Speaker_recognition" title="Speaker recognition">speaker verification</a> to achieve text-to-speech synthesis, that can be made to sound almost like anybody from a speech sample of only 5 seconds.<sup id="cite_ref-GoogleLearningTransferToTTS2018_85-0" class="reference"><a href="#cite_note-GoogleLearningTransferToTTS2018-85"><span class="cite-bracket">[</span>85<span class="cite-bracket">]</span></a></sup> </p><p>Also researchers from <a href="/wiki/Baidu_Research" class="mw-redirect" title="Baidu Research">Baidu Research</a> presented a <a href="/wiki/Voice_cloning" class="mw-redirect" title="Voice cloning">voice cloning</a> system with similar aims at the 2018 NeurIPS conference,<sup id="cite_ref-Baidu2018_86-0" class="reference"><a href="#cite_note-Baidu2018-86"><span class="cite-bracket">[</span>86<span class="cite-bracket">]</span></a></sup> though the result is rather unconvincing. </p><p>By 2019 the digital sound-alikes found their way to the hands of criminals as <a href="/wiki/NortonLifeLock" class="mw-redirect" title="NortonLifeLock">Symantec</a> researchers know of 3 cases where digital sound-alikes technology has been used for crime.<sup id="cite_ref-BBC2019_87-0" class="reference"><a href="#cite_note-BBC2019-87"><span class="cite-bracket">[</span>87<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-WaPo2019_88-0" class="reference"><a href="#cite_note-WaPo2019-88"><span class="cite-bracket">[</span>88<span class="cite-bracket">]</span></a></sup> </p><p>This increases the stress on the disinformation situation coupled with the facts that </p> <ul><li><a href="/wiki/Human_image_synthesis" title="Human image synthesis">Human image synthesis</a> since the early 2000s has improved beyond the point of human's inability to tell a real human imaged with a real camera from a simulation of a human imaged with a simulation of a camera.</li> <li>2D video forgery techniques were presented in 2016 that allow <a href="/wiki/Real-time_computing#Near_real-time" title="Real-time computing">near real-time</a> counterfeiting of <a href="/wiki/Facial_expressions" class="mw-redirect" title="Facial expressions">facial expressions</a> in existing 2D video.<sup id="cite_ref-Thi2016_89-0" class="reference"><a href="#cite_note-Thi2016-89"><span class="cite-bracket">[</span>89<span class="cite-bracket">]</span></a></sup></li> <li>In <a href="/wiki/SIGGRAPH" title="SIGGRAPH">SIGGRAPH</a> 2017 an audio driven digital look-alike of upper torso of Barack Obama was presented by researchers from <a href="/wiki/University_of_Washington" title="University of Washington">University of Washington</a>. It was driven only by a voice track as source data for the animation after the training phase to acquire <a href="/wiki/Lip_sync" title="Lip sync">lip sync</a> and wider facial information from training material consisting of 2D videos with audio had been completed.<sup id="cite_ref-Suw2017_90-0" class="reference"><a href="#cite_note-Suw2017-90"><span class="cite-bracket">[</span>90<span class="cite-bracket">]</span></a></sup></li></ul> <p>In March 2020, a <a href="/wiki/Freeware" title="Freeware">freeware</a> web application called <a href="/wiki/15.ai" title="15.ai">15.ai</a> that generates high-quality voices from an assortment of fictional characters from a variety of media sources was released.<sup id="cite_ref-Batch042020_91-0" class="reference"><a href="#cite_note-Batch042020-91"><span class="cite-bracket">[</span>91<span class="cite-bracket">]</span></a></sup> Initial characters included <a href="/wiki/GLaDOS" title="GLaDOS">GLaDOS</a> from <i><a href="/wiki/Portal_(series)" title="Portal (series)">Portal</a></i>, <a href="/wiki/Twilight_Sparkle" title="Twilight Sparkle">Twilight Sparkle</a> and <a href="/wiki/Fluttershy" class="mw-redirect" title="Fluttershy">Fluttershy</a> from the show <i><a href="/wiki/My_Little_Pony:_Friendship_Is_Magic" title="My Little Pony: Friendship Is Magic">My Little Pony: Friendship Is Magic</a></i>, and the <a href="/wiki/Tenth_Doctor" title="Tenth Doctor">Tenth Doctor</a> from <i><a href="/wiki/Doctor_Who" title="Doctor Who">Doctor Who</a></i>. </p> <div class="mw-heading mw-heading2"><h2 id="Speech_synthesis_markup_languages">Speech synthesis markup languages</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=36" title="Edit section: Speech synthesis markup languages"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>A number of <a href="/wiki/Markup_language" title="Markup language">markup languages</a> have been established for the rendition of text as speech in an <a href="/wiki/XML" title="XML">XML</a>-compliant format. The most recent is <a href="/wiki/Speech_Synthesis_Markup_Language" title="Speech Synthesis Markup Language">Speech Synthesis Markup Language</a> (SSML), which became a <a href="/wiki/W3C_recommendation" class="mw-redirect" title="W3C recommendation">W3C recommendation</a> in 2004. Older speech synthesis markup languages include Java Speech Markup Language (<a href="/wiki/JSML" class="mw-redirect" title="JSML">JSML</a>) and <a href="/wiki/SABLE" title="SABLE">SABLE</a>. Although each of these was proposed as a standard, none of them have been widely adopted.<sup class="noprint Inline-Template Template-Fact" style="white-space:nowrap;">[<i><a href="/wiki/Wikipedia:Citation_needed" title="Wikipedia:Citation needed"><span title="This claim needs references to reliable sources. (January 2022)">citation needed</span></a></i>]</sup> </p><p>Speech synthesis markup languages are distinguished from dialogue markup languages. <a href="/wiki/VoiceXML" title="VoiceXML">VoiceXML</a>, for example, includes tags related to speech recognition, dialogue management and touchtone dialing, in addition to text-to-speech markup.<sup class="noprint Inline-Template Template-Fact" style="white-space:nowrap;">[<i><a href="/wiki/Wikipedia:Citation_needed" title="Wikipedia:Citation needed"><span title="This claim needs references to reliable sources. (January 2022)">citation needed</span></a></i>]</sup> </p> <div class="mw-heading mw-heading2"><h2 id="Applications">Applications</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=37" title="Edit section: Applications"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <p>Speech synthesis has long been a vital assistive technology tool and its application in this area is significant and widespread. It allows environmental barriers to be removed for people with a wide range of disabilities. The longest application has been in the use of <a href="/wiki/Screen_reader" title="Screen reader">screen readers</a> for people with visual impairment, but text-to-speech systems are now commonly used by people with <a href="/wiki/Dyslexia" title="Dyslexia">dyslexia</a> and other <a href="/wiki/Reading_disability" title="Reading disability">reading disabilities</a> as well as by pre-literate children.<sup id="cite_ref-92" class="reference"><a href="#cite_note-92"><span class="cite-bracket">[</span>92<span class="cite-bracket">]</span></a></sup> They are also frequently employed to aid those with severe <a href="/wiki/Speech_impairment" class="mw-redirect" title="Speech impairment">speech impairment</a> usually through a dedicated <a href="/wiki/Voice_output_communication_aid" class="mw-redirect" title="Voice output communication aid">voice output communication aid</a>.<sup id="cite_ref-93" class="reference"><a href="#cite_note-93"><span class="cite-bracket">[</span>93<span class="cite-bracket">]</span></a></sup> Work to personalize a synthetic voice to better match a person's personality or historical voice is becoming available.<sup id="cite_ref-94" class="reference"><a href="#cite_note-94"><span class="cite-bracket">[</span>94<span class="cite-bracket">]</span></a></sup> A noted application, of speech synthesis, was the <a href="/wiki/Reading_machine" title="Reading machine">Kurzweil Reading Machine for the Blind</a> which incorporated text-to-phonetics software based on work from <a href="/wiki/Haskins_Laboratories" title="Haskins Laboratories">Haskins Laboratories</a> and a black-box synthesizer built by <a href="/wiki/Votrax" title="Votrax">Votrax</a>.<sup id="cite_ref-95" class="reference"><a href="#cite_note-95"><span class="cite-bracket">[</span>95<span class="cite-bracket">]</span></a></sup> </p> <figure class="mw-default-size mw-halign-left" typeof="mw:File/Thumb"><a href="/wiki/File:Stephen_Hawking.StarChild.jpg" class="mw-file-description"><img src="//upload.wikimedia.org/wikipedia/commons/thumb/e/eb/Stephen_Hawking.StarChild.jpg/150px-Stephen_Hawking.StarChild.jpg" decoding="async" width="150" height="215" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/e/eb/Stephen_Hawking.StarChild.jpg/225px-Stephen_Hawking.StarChild.jpg 1.5x, //upload.wikimedia.org/wikipedia/commons/e/eb/Stephen_Hawking.StarChild.jpg 2x" data-file-width="250" data-file-height="359" /></a><figcaption><a href="/wiki/Stephen_Hawking" title="Stephen Hawking">Stephen Hawking</a> was one of the most famous people to use a speech computer to communicate.</figcaption></figure> <p>Speech synthesis techniques are also used in entertainment productions such as games and animations. In 2007, Animo Limited announced the development of a software application package based on its speech synthesis software FineSpeech, explicitly geared towards customers in the entertainment industries, able to generate narration and lines of dialogue according to user specifications.<sup id="cite_ref-96" class="reference"><a href="#cite_note-96"><span class="cite-bracket">[</span>96<span class="cite-bracket">]</span></a></sup> The application reached maturity in 2008, when NEC <a href="/wiki/Biglobe" class="mw-redirect" title="Biglobe">Biglobe</a> announced a web service that allows users to create phrases from the voices of characters from the Japanese <a href="/wiki/Anime" title="Anime">anime</a> series <i><a href="/wiki/Code_Geass:_Lelouch_of_the_Rebellion_R2" class="mw-redirect" title="Code Geass: Lelouch of the Rebellion R2">Code Geass: Lelouch of the Rebellion R2</a></i>.<sup id="cite_ref-97" class="reference"><a href="#cite_note-97"><span class="cite-bracket">[</span>97<span class="cite-bracket">]</span></a></sup> 15.ai has been frequently used for <a href="/wiki/Content_creation" title="Content creation">content creation</a> in various <a href="/wiki/Fandom" title="Fandom">fandoms</a>, including the <a href="/wiki/My_Little_Pony:_Friendship_Is_Magic_fandom" title="My Little Pony: Friendship Is Magic fandom"><i>My Little Pony: Friendship Is Magic</i> fandom</a>, the <i><a href="/wiki/Team_Fortress_2" title="Team Fortress 2">Team Fortress 2</a></i> fandom, the <i><a href="/wiki/Portal_(series)" title="Portal (series)">Portal</a></i> fandom, and the <i><a href="/wiki/SpongeBob_SquarePants" title="SpongeBob SquarePants">SpongeBob SquarePants</a></i> fandom.<sup class="noprint Inline-Template Template-Fact" style="white-space:nowrap;">[<i><a href="/wiki/Wikipedia:Citation_needed" title="Wikipedia:Citation needed"><span title="This claim needs references to reliable sources. (June 2024)">citation needed</span></a></i>]</sup> </p><p>Text-to-speech for disability and impaired communication aids have become widely available. Text-to-speech is also finding new applications; for example, speech synthesis combined with <a href="/wiki/Speech_recognition" title="Speech recognition">speech recognition</a> allows for interaction with mobile devices via <a href="/wiki/Natural_language_processing" title="Natural language processing">natural language processing</a> interfaces. Some users have also created AI <a href="/wiki/Virtual_assistant" title="Virtual assistant">virtual assistants</a> using 15.ai and external voice control software.<sup id="cite_ref-automaton2_51-1" class="reference"><a href="#cite_note-automaton2-51"><span class="cite-bracket">[</span>51<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-Denfaminicogamer2_52-1" class="reference"><a href="#cite_note-Denfaminicogamer2-52"><span class="cite-bracket">[</span>52<span class="cite-bracket">]</span></a></sup> </p><p>Text-to-speech is also used in second language acquisition. Voki, for instance, is an educational tool created by Oddcast that allows users to create their own talking avatar, using different accents. They can be emailed, embedded on websites or shared on social media. </p><p>Content creators have used voice cloning tools to recreate their voices for podcasts,<sup id="cite_ref-:162_98-0" class="reference"><a href="#cite_note-:162-98"><span class="cite-bracket">[</span>98<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-99" class="reference"><a href="#cite_note-99"><span class="cite-bracket">[</span>99<span class="cite-bracket">]</span></a></sup> narration,<sup id="cite_ref-:13_54-1" class="reference"><a href="#cite_note-:13-54"><span class="cite-bracket">[</span>54<span class="cite-bracket">]</span></a></sup> and comedy shows.<sup id="cite_ref-100" class="reference"><a href="#cite_note-100"><span class="cite-bracket">[</span>100<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-101" class="reference"><a href="#cite_note-101"><span class="cite-bracket">[</span>101<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-102" class="reference"><a href="#cite_note-102"><span class="cite-bracket">[</span>102<span class="cite-bracket">]</span></a></sup> Publishers and authors have also used such software to narrate audiobooks and newsletters.<sup id="cite_ref-:2_103-0" class="reference"><a href="#cite_note-:2-103"><span class="cite-bracket">[</span>103<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-:02_104-0" class="reference"><a href="#cite_note-:02-104"><span class="cite-bracket">[</span>104<span class="cite-bracket">]</span></a></sup> Another area of application is AI video creation with talking heads. Webapps and video editors like Elai.io or <a href="/wiki/Synthesia_(company)" title="Synthesia (company)">Synthesia</a> allow users to create video content involving AI avatars, who are made to speak using text-to-speech technology.<sup id="cite_ref-105" class="reference"><a href="#cite_note-105"><span class="cite-bracket">[</span>105<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-106" class="reference"><a href="#cite_note-106"><span class="cite-bracket">[</span>106<span class="cite-bracket">]</span></a></sup> </p><p>Speech synthesis is a valuable computational aid for the analysis and assessment of speech disorders. A <a href="/wiki/Voice_quality" class="mw-redirect" title="Voice quality">voice quality</a> synthesizer, developed by Jorge C. Lucero et al. at the <a href="/wiki/University_of_Bras%C3%ADlia" title="University of Brasília">University of Brasília</a>, simulates the physics of <a href="/wiki/Phonation" title="Phonation">phonation</a> and includes models of vocal frequency jitter and tremor, airflow noise and laryngeal asymmetries.<sup id="cite_ref-:0_46-1" class="reference"><a href="#cite_note-:0-46"><span class="cite-bracket">[</span>46<span class="cite-bracket">]</span></a></sup> The synthesizer has been used to mimic the <a href="/wiki/Timbre" title="Timbre">timbre</a> of <a href="/wiki/Dysphonic" class="mw-redirect" title="Dysphonic">dysphonic</a> speakers with controlled levels of roughness, breathiness and strain.<sup id="cite_ref-:1_47-1" class="reference"><a href="#cite_note-:1-47"><span class="cite-bracket">[</span>47<span class="cite-bracket">]</span></a></sup> </p> <div class="mw-heading mw-heading3"><h3 id="Singing_synthesis">Singing synthesis</h3><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=38" title="Edit section: Singing synthesis"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <div class="excerpt-block"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1066933788"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1236090951"><div role="note" class="hatnote navigation-not-searchable dablink excerpt-hat selfref">This section is an excerpt from <a href="/wiki/Music_technology_(electronic_and_digital)#Vocal_synthesis_after_2010s" title="Music technology (electronic and digital)">Music technology (electronic and digital) § Vocal synthesis after 2010s</a>.<span class="mw-editsection-like plainlinks"><span class="mw-editsection-bracket">[</span><a class="external text" href="https://en.wikipedia.org/w/index.php?title=Music_technology_(electronic_and_digital)&action=edit">edit</a><span class="mw-editsection-bracket">]</span></span></div><div class="excerpt"> In the 2010s, Singing synthesis technology has taken advantage of the recent advances in artificial intelligence—deep listening and machine learning to better represent the nuances of the human voice. New high fidelity sample libraries combined with digital audio workstations facilitate editing in fine detail, such as shifting of formats, adjustment of vibrato, and adjustments to vowels and consonants. Sample libraries for various languages and various accents are available. With today's advancements in vocal synthesis, artists sometimes use sample libraries in lieu of backing singers.<sup id="cite_ref-107" class="reference"><a href="#cite_note-107"><span class="cite-bracket">[</span>107<span class="cite-bracket">]</span></a></sup></div></div> <div class="mw-heading mw-heading2"><h2 id="See_also">See also</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=39" title="Edit section: See also"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <style data-mw-deduplicate="TemplateStyles:r1184024115">.mw-parser-output .div-col{margin-top:0.3em;column-width:30em}.mw-parser-output .div-col-small{font-size:90%}.mw-parser-output .div-col-rules{column-rule:1px solid #aaa}.mw-parser-output .div-col dl,.mw-parser-output .div-col ol,.mw-parser-output .div-col ul{margin-top:0}.mw-parser-output .div-col li,.mw-parser-output .div-col dd{page-break-inside:avoid;break-inside:avoid-column}</style><div class="div-col" style="column-width: 22em;"> <ul><li><a href="/wiki/Chinese_speech_synthesis" title="Chinese speech synthesis">Chinese speech synthesis</a></li> <li><a href="/wiki/Comparison_of_speech_synthesizers" title="Comparison of speech synthesizers">Comparison of speech synthesizers</a></li> <li><a href="/wiki/List_of_screen_readers" title="List of screen readers">List of screen readers</a></li> <li><a href="/wiki/Orca_(assistive_technology)" title="Orca (assistive technology)">Orca (assistive technology)</a></li> <li><a href="/wiki/Paperless_office" title="Paperless office">Paperless office</a></li> <li><a href="/wiki/Silent_speech_interface" class="mw-redirect" title="Silent speech interface">Silent speech interface</a></li> <li><a href="/wiki/Speech-generating_device" title="Speech-generating device">Speech-generating device</a></li> <li><a href="/wiki/Speech_processing" title="Speech processing">Speech processing</a></li> <li><a href="/wiki/Text_to_speech_in_digital_television" title="Text to speech in digital television">Text to speech in digital television</a></li></ul></div> <div class="mw-heading mw-heading2"><h2 id="References">References</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=40" title="Edit section: References"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <style data-mw-deduplicate="TemplateStyles:r1239543626">.mw-parser-output .reflist{margin-bottom:0.5em;list-style-type:decimal}@media screen{.mw-parser-output .reflist{font-size:90%}}.mw-parser-output .reflist .references{font-size:100%;margin-bottom:0;list-style-type:inherit}.mw-parser-output .reflist-columns-2{column-width:30em}.mw-parser-output .reflist-columns-3{column-width:25em}.mw-parser-output .reflist-columns{margin-top:0.3em}.mw-parser-output .reflist-columns ol{margin-top:0}.mw-parser-output .reflist-columns li{page-break-inside:avoid;break-inside:avoid-column}.mw-parser-output .reflist-upper-alpha{list-style-type:upper-alpha}.mw-parser-output .reflist-upper-roman{list-style-type:upper-roman}.mw-parser-output .reflist-lower-alpha{list-style-type:lower-alpha}.mw-parser-output .reflist-lower-greek{list-style-type:lower-greek}.mw-parser-output .reflist-lower-roman{list-style-type:lower-roman}</style><div class="reflist"> <div class="mw-references-wrap mw-references-columns"><ol class="references"> <li id="cite_note-1"><span class="mw-cite-backlink"><b><a href="#cite_ref-1">^</a></b></span> <span class="reference-text"><style data-mw-deduplicate="TemplateStyles:r1238218222">.mw-parser-output cite.citation{font-style:inherit;word-wrap:break-word}.mw-parser-output .citation q{quotes:"\"""\"""'""'"}.mw-parser-output .citation:target{background-color:rgba(0,127,255,0.133)}.mw-parser-output .id-lock-free.id-lock-free a{background:url("//upload.wikimedia.org/wikipedia/commons/6/65/Lock-green.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-limited.id-lock-limited a,.mw-parser-output .id-lock-registration.id-lock-registration a{background:url("//upload.wikimedia.org/wikipedia/commons/d/d6/Lock-gray-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-subscription.id-lock-subscription a{background:url("//upload.wikimedia.org/wikipedia/commons/a/aa/Lock-red-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .cs1-ws-icon a{background:url("//upload.wikimedia.org/wikipedia/commons/4/4c/Wikisource-logo.svg")right 0.1em center/12px no-repeat}body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-free a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-limited a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-registration a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-subscription a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .cs1-ws-icon a{background-size:contain;padding:0 1em 0 0}.mw-parser-output .cs1-code{color:inherit;background:inherit;border:none;padding:inherit}.mw-parser-output .cs1-hidden-error{display:none;color:var(--color-error,#d33)}.mw-parser-output .cs1-visible-error{color:var(--color-error,#d33)}.mw-parser-output .cs1-maint{display:none;color:#085;margin-left:0.3em}.mw-parser-output .cs1-kern-left{padding-left:0.2em}.mw-parser-output .cs1-kern-right{padding-right:0.2em}.mw-parser-output .citation .mw-selflink{font-weight:inherit}@media screen{.mw-parser-output .cs1-format{font-size:95%}html.skin-theme-clientpref-night .mw-parser-output .cs1-maint{color:#18911f}}@media screen and (prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .cs1-maint{color:#18911f}}</style><cite id="CITEREFAllenHunnicuttKlatt1987" class="citation book cs1">Allen, Jonathan; Hunnicutt, M. Sharon; Klatt, Dennis (1987). <span class="id-lock-registration" title="Free registration required"><a rel="nofollow" class="external text" href="https://archive.org/details/fromtexttospeech00alle"><i>From Text to Speech: The MITalk system</i></a></span>. Cambridge University Press. <a href="/wiki/ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <a href="/wiki/Special:BookSources/978-0-521-30641-6" title="Special:BookSources/978-0-521-30641-6"><bdi>978-0-521-30641-6</bdi></a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.btitle=From+Text+to+Speech%3A+The+MITalk+system&rft.pub=Cambridge+University+Press&rft.date=1987&rft.isbn=978-0-521-30641-6&rft.aulast=Allen&rft.aufirst=Jonathan&rft.au=Hunnicutt%2C+M.+Sharon&rft.au=Klatt%2C+Dennis&rft_id=https%3A%2F%2Farchive.org%2Fdetails%2Ffromtexttospeech00alle&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-2"><span class="mw-cite-backlink"><b><a href="#cite_ref-2">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFRubinBaerMermelstein1981" class="citation journal cs1">Rubin, P.; Baer, T.; Mermelstein, P. (1981). "An articulatory synthesizer for perceptual research". <i>Journal of the Acoustical Society of America</i>. <b>70</b> (2): 321–328. <a href="/wiki/Bibcode_(identifier)" class="mw-redirect" title="Bibcode (identifier)">Bibcode</a>:<a rel="nofollow" class="external text" href="https://ui.adsabs.harvard.edu/abs/1981ASAJ...70..321R">1981ASAJ...70..321R</a>. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1121%2F1.386780">10.1121/1.386780</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Journal+of+the+Acoustical+Society+of+America&rft.atitle=An+articulatory+synthesizer+for+perceptual+research&rft.volume=70&rft.issue=2&rft.pages=321-328&rft.date=1981&rft_id=info%3Adoi%2F10.1121%2F1.386780&rft_id=info%3Abibcode%2F1981ASAJ...70..321R&rft.aulast=Rubin&rft.aufirst=P.&rft.au=Baer%2C+T.&rft.au=Mermelstein%2C+P.&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-3"><span class="mw-cite-backlink"><b><a href="#cite_ref-3">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFvan_SantenSproatOliveHirschberg1997" class="citation book cs1">van Santen, Jan P. H.; Sproat, Richard W.; Olive, Joseph P.; Hirschberg, Julia (1997). <span class="id-lock-registration" title="Free registration required"><a rel="nofollow" class="external text" href="https://archive.org/details/progressinspeech0000unse"><i>Progress in Speech Synthesis</i></a></span>. Springer. <a href="/wiki/ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <a href="/wiki/Special:BookSources/978-0-387-94701-3" title="Special:BookSources/978-0-387-94701-3"><bdi>978-0-387-94701-3</bdi></a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.btitle=Progress+in+Speech+Synthesis&rft.pub=Springer&rft.date=1997&rft.isbn=978-0-387-94701-3&rft.aulast=van+Santen&rft.aufirst=Jan+P.+H.&rft.au=Sproat%2C+Richard+W.&rft.au=Olive%2C+Joseph+P.&rft.au=Hirschberg%2C+Julia&rft_id=https%3A%2F%2Farchive.org%2Fdetails%2Fprogressinspeech0000unse&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-4"><span class="mw-cite-backlink"><b><a href="#cite_ref-4">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFVan_Santen1994" class="citation journal cs1">Van Santen, J. (April 1994). "Assignment of segmental duration in text-to-speech synthesis". <i>Computer Speech & Language</i>. <b>8</b> (2): 95–128. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1006%2Fcsla.1994.1005">10.1006/csla.1994.1005</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Computer+Speech+%26+Language&rft.atitle=Assignment+of+segmental+duration+in+text-to-speech+synthesis&rft.volume=8&rft.issue=2&rft.pages=95-128&rft.date=1994-04&rft_id=info%3Adoi%2F10.1006%2Fcsla.1994.1005&rft.aulast=Van+Santen&rft.aufirst=J.&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-Helsinki-5"><span class="mw-cite-backlink"><b><a href="#cite_ref-Helsinki_5-0">^</a></b></span> <span class="reference-text"><a rel="nofollow" class="external text" href="http://www.acoustics.hut.fi/publications/files/theses/lemmetty_mst/chap2.html">History and Development of Speech Synthesis</a>, Helsinki University of Technology, Retrieved on November 4, 2006</span> </li> <li id="cite_note-6"><span class="mw-cite-backlink"><b><a href="#cite_ref-6">^</a></b></span> <span class="reference-text"><i>Mechanismus der menschlichen Sprache nebst der Beschreibung seiner sprechenden Maschine</i> ("Mechanism of the human speech with description of its speaking machine", J. B. Degen, Wien). <span class="languageicon">(in German)</span></span> </li> <li id="cite_note-7"><span class="mw-cite-backlink"><b><a href="#cite_ref-7">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFMattingly1974" class="citation journal cs1">Mattingly, Ignatius G. (1974). Sebeok, Thomas A. (ed.). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20130512085755/http://www.haskins.yale.edu/Reprints/HL0173.pdf">"Speech synthesis for phonetic and phonological models"</a> <span class="cs1-format">(PDF)</span>. <i>Current Trends in Linguistics</i>. <b>12</b>. Mouton, The Hague: 2451–2487. Archived from <a rel="nofollow" class="external text" href="http://www.haskins.yale.edu/Reprints/HL0173.pdf">the original</a> <span class="cs1-format">(PDF)</span> on 2013-05-12<span class="reference-accessdate">. Retrieved <span class="nowrap">2011-12-13</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Current+Trends+in+Linguistics&rft.atitle=Speech+synthesis+for+phonetic+and+phonological+models&rft.volume=12&rft.pages=2451-2487&rft.date=1974&rft.aulast=Mattingly&rft.aufirst=Ignatius+G.&rft_id=http%3A%2F%2Fwww.haskins.yale.edu%2FReprints%2FHL0173.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-8"><span class="mw-cite-backlink"><b><a href="#cite_ref-8">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFKlatt1987" class="citation journal cs1">Klatt, D (1987). "Review of text-to-speech conversion for English". <i>Journal of the Acoustical Society of America</i>. <b>82</b> (3): 737–93. <a href="/wiki/Bibcode_(identifier)" class="mw-redirect" title="Bibcode (identifier)">Bibcode</a>:<a rel="nofollow" class="external text" href="https://ui.adsabs.harvard.edu/abs/1987ASAJ...82..737K">1987ASAJ...82..737K</a>. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1121%2F1.395275">10.1121/1.395275</a>. <a href="/wiki/PMID_(identifier)" class="mw-redirect" title="PMID (identifier)">PMID</a> <a rel="nofollow" class="external text" href="https://pubmed.ncbi.nlm.nih.gov/2958525">2958525</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Journal+of+the+Acoustical+Society+of+America&rft.atitle=Review+of+text-to-speech+conversion+for+English&rft.volume=82&rft.issue=3&rft.pages=737-93&rft.date=1987&rft_id=info%3Apmid%2F2958525&rft_id=info%3Adoi%2F10.1121%2F1.395275&rft_id=info%3Abibcode%2F1987ASAJ...82..737K&rft.aulast=Klatt&rft.aufirst=D&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-9"><span class="mw-cite-backlink"><b><a href="#cite_ref-9">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFLambert1992" class="citation news cs1">Lambert, Bruce (March 21, 1992). <a rel="nofollow" class="external text" href="https://www.nytimes.com/1992/03/21/nyregion/louis-gerstman-61-a-specialist-in-speech-disorders-and-processes.html">"Louis Gerstman, 61, a Specialist In Speech Disorders and Processes"</a>. <i>The New York Times</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=The+New+York+Times&rft.atitle=Louis+Gerstman%2C+61%2C+a+Specialist+In+Speech+Disorders+and+Processes&rft.date=1992-03-21&rft.aulast=Lambert&rft.aufirst=Bruce&rft_id=https%3A%2F%2Fwww.nytimes.com%2F1992%2F03%2F21%2Fnyregion%2Flouis-gerstman-61-a-specialist-in-speech-disorders-and-processes.html&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-10"><span class="mw-cite-backlink"><b><a href="#cite_ref-10">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/19971211154551/http://www.lsi.usp.br/~rbianchi/clarke/ACC.Biography.html">"Arthur C. Clarke Biography"</a>. Archived from <a rel="nofollow" class="external text" href="http://www.lsi.usp.br/~rbianchi/clarke/ACC.Biography.html">the original</a> on December 11, 1997<span class="reference-accessdate">. Retrieved <span class="nowrap">5 December</span> 2017</span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=Arthur+C.+Clarke+Biography&rft_id=http%3A%2F%2Fwww.lsi.usp.br%2F~rbianchi%2Fclarke%2FACC.Biography.html&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-11"><span class="mw-cite-backlink"><b><a href="#cite_ref-11">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/20000407081031/http://www.bell-labs.com/news/1997/march/5/2.html">"Where "HAL" First Spoke (Bell Labs Speech Synthesis website)"</a>. Bell Labs. Archived from <a rel="nofollow" class="external text" href="http://www.bell-labs.com/news/1997/march/5/2.html">the original</a> on 2000-04-07<span class="reference-accessdate">. Retrieved <span class="nowrap">2010-02-17</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=Where+%22HAL%22+First+Spoke+%28Bell+Labs+Speech+Synthesis+website%29&rft.pub=Bell+Labs&rft_id=http%3A%2F%2Fwww.bell-labs.com%2Fnews%2F1997%2Fmarch%2F5%2F2.html&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-12"><span class="mw-cite-backlink"><b><a href="#cite_ref-12">^</a></b></span> <span class="reference-text"><a rel="nofollow" class="external text" href="http://www.takanishi.mech.waseda.ac.jp/top/research/voice/index.htm">Anthropomorphic Talking Robot Waseda-Talker Series</a> <a rel="nofollow" class="external text" href="https://web.archive.org/web/20160304034116/http://www.takanishi.mech.waseda.ac.jp/top/research/voice/index.htm">Archived</a> 2016-03-04 at the <a href="/wiki/Wayback_Machine" title="Wayback Machine">Wayback Machine</a></span> </li> <li id="cite_note-13"><span class="mw-cite-backlink"><b><a href="#cite_ref-13">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFGray2010" class="citation journal cs1">Gray, Robert M. (2010). <a rel="nofollow" class="external text" href="https://ee.stanford.edu/~gray/lpcip.pdf">"A History of Realtime Digital Speech on Packet Networks: Part II of Linear Predictive Coding and the Internet Protocol"</a> <span class="cs1-format">(PDF)</span>. <i>Found. Trends Signal Process</i>. <b>3</b> (4): 203–303. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://doi.org/10.1561%2F2000000036">10.1561/2000000036</a></span>. <a href="/wiki/ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/1932-8346">1932-8346</a>. <a rel="nofollow" class="external text" href="https://ghostarchive.org/archive/20221009/https://ee.stanford.edu/~gray/lpcip.pdf">Archived</a> <span class="cs1-format">(PDF)</span> from the original on 2022-10-09.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Found.+Trends+Signal+Process.&rft.atitle=A+History+of+Realtime+Digital+Speech+on+Packet+Networks%3A+Part+II+of+Linear+Predictive+Coding+and+the+Internet+Protocol&rft.volume=3&rft.issue=4&rft.pages=203-303&rft.date=2010&rft_id=info%3Adoi%2F10.1561%2F2000000036&rft.issn=1932-8346&rft.aulast=Gray&rft.aufirst=Robert+M.&rft_id=https%3A%2F%2Fee.stanford.edu%2F~gray%2Flpcip.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-14"><span class="mw-cite-backlink"><b><a href="#cite_ref-14">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFZhengSongLiYu1998" class="citation journal cs1">Zheng, F.; Song, Z.; Li, L.; Yu, W. (1998). <a rel="nofollow" class="external text" href="http://www.work.caltech.edu/~ling/pub/icslp98lsp.pdf">"The Distance Measure for Line Spectrum Pairs Applied to Speech Recognition"</a> <span class="cs1-format">(PDF)</span>. <i>Proceedings of the 5th International Conference on Spoken Language Processing (ICSLP'98)</i> (3): 1123–6. <a rel="nofollow" class="external text" href="https://ghostarchive.org/archive/20221009/http://www.work.caltech.edu/~ling/pub/icslp98lsp.pdf">Archived</a> <span class="cs1-format">(PDF)</span> from the original on 2022-10-09.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Proceedings+of+the+5th+International+Conference+on+Spoken+Language+Processing+%28ICSLP%2798%29&rft.atitle=The+Distance+Measure+for+Line+Spectrum+Pairs+Applied+to+Speech+Recognition&rft.issue=3&rft.pages=1123-6&rft.date=1998&rft.aulast=Zheng&rft.aufirst=F.&rft.au=Song%2C+Z.&rft.au=Li%2C+L.&rft.au=Yu%2C+W.&rft_id=http%3A%2F%2Fwww.work.caltech.edu%2F~ling%2Fpub%2Ficslp98lsp.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-ieee-15"><span class="mw-cite-backlink">^ <a href="#cite_ref-ieee_15-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-ieee_15-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://ethw.org/Milestones:List_of_IEEE_Milestones">"List of IEEE Milestones"</a>. <a href="/wiki/IEEE" class="mw-redirect" title="IEEE">IEEE</a><span class="reference-accessdate">. Retrieved <span class="nowrap">15 July</span> 2019</span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=List+of+IEEE+Milestones&rft.pub=IEEE&rft_id=https%3A%2F%2Fethw.org%2FMilestones%3AList_of_IEEE_Milestones&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-ItakuraHistory-16"><span class="mw-cite-backlink">^ <a href="#cite_ref-ItakuraHistory_16-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-ItakuraHistory_16-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://ethw.org/Oral-History:Fumitada_Itakura">"Fumitada Itakura Oral History"</a>. IEEE Global History Network. 20 May 2009<span class="reference-accessdate">. Retrieved <span class="nowrap">2009-07-21</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=Fumitada+Itakura+Oral+History&rft.pub=IEEE+Global+History+Network&rft.date=2009-05-20&rft_id=https%3A%2F%2Fethw.org%2FOral-History%3AFumitada_Itakura&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-17"><span class="mw-cite-backlink"><b><a href="#cite_ref-17">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFBilliCanavesioCiaramellaNebbia1995" class="citation journal cs1">Billi, Roberto; Canavesio, Franco; <a href="/wiki/Alberto_Ciaramella" title="Alberto Ciaramella">Ciaramella, Alberto</a>; Nebbia, Luciano (1 November 1995). "Interactive voice technology at work: The CSELT experience". <i>Speech Communication</i>. <b>17</b> (3): 263–271. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1016%2F0167-6393%2895%2900030-R">10.1016/0167-6393(95)00030-R</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Speech+Communication&rft.atitle=Interactive+voice+technology+at+work%3A+The+CSELT+experience&rft.volume=17&rft.issue=3&rft.pages=263-271&rft.date=1995-11-01&rft_id=info%3Adoi%2F10.1016%2F0167-6393%2895%2900030-R&rft.aulast=Billi&rft.aufirst=Roberto&rft.au=Canavesio%2C+Franco&rft.au=Ciaramella%2C+Alberto&rft.au=Nebbia%2C+Luciano&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-18"><span class="mw-cite-backlink"><b><a href="#cite_ref-18">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFSproat1997" class="citation book cs1">Sproat, Richard W. (1997). <i>Multilingual Text-to-Speech Synthesis: The Bell Labs Approach</i>. Springer. <a href="/wiki/ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <a href="/wiki/Special:BookSources/978-0-7923-8027-6" title="Special:BookSources/978-0-7923-8027-6"><bdi>978-0-7923-8027-6</bdi></a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.btitle=Multilingual+Text-to-Speech+Synthesis%3A+The+Bell+Labs+Approach&rft.pub=Springer&rft.date=1997&rft.isbn=978-0-7923-8027-6&rft.aulast=Sproat&rft.aufirst=Richard+W.&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-19"><span class="mw-cite-backlink"><b><a href="#cite_ref-19">^</a></b></span> <span class="reference-text">[TSI Speech+ & other speaking calculators]</span> </li> <li id="cite_note-20"><span class="mw-cite-backlink"><b><a href="#cite_ref-20">^</a></b></span> <span class="reference-text">Gevaryahu, Jonathan, [ "TSI S14001A Speech Synthesizer LSI Integrated Circuit Guide"]<sup class="noprint Inline-Template"><span style="white-space: nowrap;">[<i><a href="/wiki/Wikipedia:Link_rot" title="Wikipedia:Link rot"><span title=" Dead link tagged December 2011">dead link</span></a></i><span style="visibility:hidden; color:transparent; padding-left:2px">‍</span>]</span></sup></span> </li> <li id="cite_note-21"><span class="mw-cite-backlink"><b><a href="#cite_ref-21">^</a></b></span> <span class="reference-text">Breslow, et al. <style data-mw-deduplicate="TemplateStyles:r1041539562">.mw-parser-output .citation{word-wrap:break-word}.mw-parser-output .citation:target{background-color:rgba(0,127,255,0.133)}</style><span class="citation patent"><a rel="nofollow" class="external text" href="https://worldwide.espacenet.com/textdoc?DB=EPODOC&IDX=US4326710">US 4326710</a></span><span class="Z3988" title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.number=4326710&rft.cc=US&rft.title="><span style="display: none;"> </span></span>: "Talking electronic game", April 27, 1982</span> </li> <li id="cite_note-22"><span class="mw-cite-backlink"><b><a href="#cite_ref-22">^</a></b></span> <span class="reference-text"><a rel="nofollow" class="external text" href="http://www.ismenio.com/chess_fidelity_vcc.html">Voice Chess Challenger</a></span> </li> <li id="cite_note-23"><span class="mw-cite-backlink"><b><a href="#cite_ref-23">^</a></b></span> <span class="reference-text"><a rel="nofollow" class="external text" href="http://www.gamesradar.com/f/gamings-most-important-evolutions/a-20101008102331322035/p-2">Gaming's most important evolutions</a> <a rel="nofollow" class="external text" href="https://web.archive.org/web/20110615221800/http://www.gamesradar.com/f/gamings-most-important-evolutions/a-20101008102331322035/p-2">Archived</a> 2011-06-15 at the <a href="/wiki/Wayback_Machine" title="Wayback Machine">Wayback Machine</a>, <a href="/wiki/GamesRadar" class="mw-redirect" title="GamesRadar">GamesRadar</a></span> </li> <li id="cite_note-24"><span class="mw-cite-backlink"><b><a href="#cite_ref-24">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFAdlum1985" class="citation magazine cs1">Adlum, Eddie (November 1985). <a rel="nofollow" class="external text" href="https://archive.org/details/re-play-volume-11-issue-no.-2-november-1985-600DPI/RePlay%20-%20Volume%2011%2C%20Issue%20No.%202%20-%20November%201985/page/162/mode/2up">"The Replay Years: Reflections from Eddie Adlum"</a>. <i>RePlay</i>. Vol. 11, no. 2. pp. 134-175 (160-3).</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=RePlay&rft.atitle=The+Replay+Years%3A+Reflections+from+Eddie+Adlum&rft.volume=11&rft.issue=2&rft.pages=134-175+%28160-3%29&rft.date=1985-11&rft.aulast=Adlum&rft.aufirst=Eddie&rft_id=https%3A%2F%2Farchive.org%2Fdetails%2Fre-play-volume-11-issue-no.-2-november-1985-600DPI%2FRePlay%2520-%2520Volume%252011%252C%2520Issue%2520No.%25202%2520-%2520November%25201985%2Fpage%2F162%2Fmode%2F2up&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-25"><span class="mw-cite-backlink"><b><a href="#cite_ref-25">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFSzczepaniak2014" class="citation book cs1">Szczepaniak, John (2014). <i>The Untold History of Japanese Game Developers</i>. Vol. 1. SMG Szczepaniak. pp. 544–615. <a href="/wiki/ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <a href="/wiki/Special:BookSources/978-0992926007" title="Special:BookSources/978-0992926007"><bdi>978-0992926007</bdi></a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.btitle=The+Untold+History+of+Japanese+Game+Developers&rft.pages=544-615&rft.pub=SMG+Szczepaniak&rft.date=2014&rft.isbn=978-0992926007&rft.aulast=Szczepaniak&rft.aufirst=John&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-26"><span class="mw-cite-backlink"><b><a href="#cite_ref-26">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation news cs1"><a rel="nofollow" class="external text" href="https://amhistory.si.edu/archives/speechsynthesis/ss_rice.htm">"A Short History of Computalker"</a>. <i>Smithsonian Speech Synthesis History Project</i>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Smithsonian+Speech+Synthesis+History+Project&rft.atitle=A+Short+History+of+Computalker&rft_id=https%3A%2F%2Famhistory.si.edu%2Farchives%2Fspeechsynthesis%2Fss_rice.htm&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-NewYorkTimes-27"><span class="mw-cite-backlink"><b><a href="#cite_ref-NewYorkTimes_27-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFCadeMetz2020" class="citation news cs1">CadeMetz (2020-08-20). <a rel="nofollow" class="external text" href="https://www.nytimes.com/2020/08/20/technology/ann-syrdal-who-helped-give-computers-a-female-voice-dies-at-74.html">"Ann Syrdal, Who Helped Give Computers a Female Voice, Dies at 74"</a>. <i>The New York Times</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2020-08-23</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=The+New+York+Times&rft.atitle=Ann+Syrdal%2C+Who+Helped+Give+Computers+a+Female+Voice%2C+Dies+at+74&rft.date=2020-08-20&rft.au=CadeMetz&rft_id=https%3A%2F%2Fwww.nytimes.com%2F2020%2F08%2F20%2Ftechnology%2Fann-syrdal-who-helped-give-computers-a-female-voice-dies-at-74.html&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-28"><span class="mw-cite-backlink"><b><a href="#cite_ref-28">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFKurzweil2005" class="citation book cs1"><a href="/wiki/Raymond_Kurzweil" class="mw-redirect" title="Raymond Kurzweil">Kurzweil, Raymond</a> (2005). <i>The Singularity is Near</i>. <a href="/wiki/Penguin_Books" title="Penguin Books">Penguin Books</a>. <a href="/wiki/ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <a href="/wiki/Special:BookSources/978-0-14-303788-0" title="Special:BookSources/978-0-14-303788-0"><bdi>978-0-14-303788-0</bdi></a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.btitle=The+Singularity+is+Near&rft.pub=Penguin+Books&rft.date=2005&rft.isbn=978-0-14-303788-0&rft.aulast=Kurzweil&rft.aufirst=Raymond&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-29"><span class="mw-cite-backlink"><b><a href="#cite_ref-29">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFTaylor2009" class="citation book cs1">Taylor, Paul (2009). <span class="id-lock-limited" title="Free access subject to limited trial, subscription normally required"><a rel="nofollow" class="external text" href="https://archive.org/details/texttospeechsynt00tayl_030"><i>Text-to-speech synthesis</i></a></span>. Cambridge, UK: Cambridge University Press. p. <a rel="nofollow" class="external text" href="https://archive.org/details/texttospeechsynt00tayl_030/page/n26">3</a>. <a href="/wiki/ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <a href="/wiki/Special:BookSources/9780521899277" title="Special:BookSources/9780521899277"><bdi>9780521899277</bdi></a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.btitle=Text-to-speech+synthesis&rft.place=Cambridge%2C+UK&rft.pages=3&rft.pub=Cambridge+University+Press&rft.date=2009&rft.isbn=9780521899277&rft.aulast=Taylor&rft.aufirst=Paul&rft_id=https%3A%2F%2Farchive.org%2Fdetails%2Ftexttospeechsynt00tayl_030&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-30"><span class="mw-cite-backlink"><b><a href="#cite_ref-30">^</a></b></span> <span class="reference-text"><a href="/wiki/Alan_W._Black" title="Alan W. Black">Alan W. Black</a>, <a rel="nofollow" class="external text" href="https://www.cs.cmu.edu/~awb/papers/IEEE2002/allthetime/allthetime.html">Perfect synthesis for all of the people all of the time.</a> IEEE TTS Workshop 2002.</span> </li> <li id="cite_note-31"><span class="mw-cite-backlink"><b><a href="#cite_ref-31">^</a></b></span> <span class="reference-text">John Kominek and <a href="/wiki/Alan_W._Black" title="Alan W. Black">Alan W. Black</a>. (2003). CMU ARCTIC databases for speech synthesis. CMU-LTI-03-177. Language Technologies Institute, School of Computer Science, Carnegie Mellon University.</span> </li> <li id="cite_note-32"><span class="mw-cite-backlink"><b><a href="#cite_ref-32">^</a></b></span> <span class="reference-text">Julia Zhang. <a rel="nofollow" class="external text" href="http://groups.csail.mit.edu/sls/publications/2004/zhang_thesis.pdf">Language Generation and Speech Synthesis in Dialogues for Language Learning</a>, masters thesis, Section 5.6 on page 54.</span> </li> <li id="cite_note-33"><span class="mw-cite-backlink"><b><a href="#cite_ref-33">^</a></b></span> <span class="reference-text">William Yang Wang and Kallirroi Georgila. (2011). <a rel="nofollow" class="external text" href="https://www.cs.cmu.edu/~yww/papers/asru2011.pdf">Automatic Detection of Unnatural Word-Level Segments in Unit-Selection Speech Synthesis</a>, IEEE ASRU 2011.</span> </li> <li id="cite_note-34"><span class="mw-cite-backlink"><b><a href="#cite_ref-34">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/20070222180903/http://www.fon.hum.uva.nl/praat/manual/PSOLA.html">"Pitch-Synchronous Overlap and Add (PSOLA) Synthesis"</a>. Archived from <a rel="nofollow" class="external text" href="http://www.fon.hum.uva.nl/praat/manual/PSOLA.html">the original</a> on February 22, 2007<span class="reference-accessdate">. Retrieved <span class="nowrap">2008-05-28</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=Pitch-Synchronous+Overlap+and+Add+%28PSOLA%29+Synthesis&rft_id=http%3A%2F%2Fwww.fon.hum.uva.nl%2Fpraat%2Fmanual%2FPSOLA.html&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-35"><span class="mw-cite-backlink"><b><a href="#cite_ref-35">^</a></b></span> <span class="reference-text">T. Dutoit, V. Pagel, N. Pierret, F. Bataille, O. van der Vrecken. <a rel="nofollow" class="external text" href="http://ai2-s2-pdfs.s3.amazonaws.com/7b1f/dadf05b8f968a5b361f6f82852ade62c8010.pdf">The MBROLA Project: Towards a set of high quality speech synthesizers of use for non commercial purposes</a>. <i>ICSLP Proceedings</i>, 1996.</span> </li> <li id="cite_note-Muralishankar2004-36"><span class="mw-cite-backlink">^ <a href="#cite_ref-Muralishankar2004_36-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-Muralishankar2004_36-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFMuralishankarRamakrishnanPrathibha2004" class="citation journal cs1">Muralishankar, R.; Ramakrishnan, A. G.; Prathibha, P. (February 2004). "Modification of Pitch using DCT in the Source Domain". <i>Speech Communication</i>. <b>42</b> (2): 143–154. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1016%2Fj.specom.2003.05.001">10.1016/j.specom.2003.05.001</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Speech+Communication&rft.atitle=Modification+of+Pitch+using+DCT+in+the+Source+Domain&rft.volume=42&rft.issue=2&rft.pages=143-154&rft.date=2004-02&rft_id=info%3Adoi%2F10.1016%2Fj.specom.2003.05.001&rft.aulast=Muralishankar&rft.aufirst=R.&rft.au=Ramakrishnan%2C+A.+G.&rft.au=Prathibha%2C+P.&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-37"><span class="mw-cite-backlink"><b><a href="#cite_ref-37">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation news cs1"><a rel="nofollow" class="external text" href="http://content.time.com/time/magazine/article/0,9171,904056,00.html">"Education: Marvel of The Bronx"</a>. <i>Time</i>. 1974-04-01. <a href="/wiki/ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/0040-781X">0040-781X</a><span class="reference-accessdate">. Retrieved <span class="nowrap">2019-05-28</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Time&rft.atitle=Education%3A+Marvel+of+The+Bronx&rft.date=1974-04-01&rft.issn=0040-781X&rft_id=http%3A%2F%2Fcontent.time.com%2Ftime%2Fmagazine%2Farticle%2F0%2C9171%2C904056%2C00.html&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-38"><span class="mw-cite-backlink"><b><a href="#cite_ref-38">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://cyberneticzoo.com/robots/1960-rudy-the-robot-michael-freeman-american/">"1960 - Rudy the Robot - Michael Freeman (American)"</a>. <i>cyberneticzoo.com</i>. 2010-09-13<span class="reference-accessdate">. Retrieved <span class="nowrap">2019-05-23</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=cyberneticzoo.com&rft.atitle=1960+-+Rudy+the+Robot+-+Michael+Freeman+%28American%29&rft.date=2010-09-13&rft_id=http%3A%2F%2Fcyberneticzoo.com%2Frobots%2F1960-rudy-the-robot-michael-freeman-american%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-39"><span class="mw-cite-backlink"><b><a href="#cite_ref-39">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation book cs1"><a rel="nofollow" class="external text" href="https://books.google.com/books?id=bNECAAAAMBAJ&q=Leachim+Michael+Freeman&pg=PA40"><i>New York Magazine</i></a>. New York Media, LLC. 1979-07-30.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.btitle=New+York+Magazine&rft.pub=New+York+Media%2C+LLC&rft.date=1979-07-30&rft_id=https%3A%2F%2Fbooks.google.com%2Fbooks%3Fid%3DbNECAAAAMBAJ%26q%3DLeachim%2BMichael%2BFreeman%26pg%3DPA40&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-40"><span class="mw-cite-backlink"><b><a href="#cite_ref-40">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation book cs1"><a rel="nofollow" class="external text" href="https://books.google.com/books?id=_QJmAAAAMAAJ&q=leachim"><i>The Futurist</i></a>. World Future Society. 1978. pp. 359, 360, 361.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.btitle=The+Futurist&rft.pages=359%2C+360%2C+361&rft.pub=World+Future+Society.&rft.date=1978&rft_id=https%3A%2F%2Fbooks.google.com%2Fbooks%3Fid%3D_QJmAAAAMAAJ%26q%3Dleachim&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-41"><span class="mw-cite-backlink"><b><a href="#cite_ref-41">^</a></b></span> <span class="reference-text"><a href="/wiki/Lori_Lamel" title="Lori Lamel">L.F. Lamel</a>, J.L. Gauvain, B. Prouts, C. Bouhier, R. Boesch. <a rel="nofollow" class="external text" href="http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.53.6101&rep=rep1&type=pdf">Generation and Synthesis of Broadcast Messages</a>, <i>Proceedings ESCA-NATO Workshop and Applications of Speech Technology</i>, September 1993.</span> </li> <li id="cite_note-42"><span class="mw-cite-backlink"><b><a href="#cite_ref-42">^</a></b></span> <span class="reference-text">Dartmouth College: <a rel="nofollow" class="external text" href="http://digitalmusics.dartmouth.edu/~book/MATCpages/chap.4/4.4.formant_synth.html"><i>Music and Computers</i></a> <a rel="nofollow" class="external text" href="https://web.archive.org/web/20110608035309/http://digitalmusics.dartmouth.edu/~book/MATCpages/chap.4/4.4.formant_synth.html">Archived</a> 2011-06-08 at the <a href="/wiki/Wayback_Machine" title="Wayback Machine">Wayback Machine</a>, 1993.</span> </li> <li id="cite_note-43"><span class="mw-cite-backlink"><b><a href="#cite_ref-43">^</a></b></span> <span class="reference-text">Examples include <a href="/wiki/Astro_Blaster" title="Astro Blaster">Astro Blaster</a>, <a href="/wiki/Space_Fury" title="Space Fury">Space Fury</a>, and <a href="/wiki/Star_Trek_(arcade_game)" title="Star Trek (arcade game)">Star Trek: Strategic Operations Simulator</a></span> </li> <li id="cite_note-44"><span class="mw-cite-backlink"><b><a href="#cite_ref-44">^</a></b></span> <span class="reference-text">Examples include <a href="/wiki/Star_Wars_(arcade_game)" class="mw-redirect" title="Star Wars (arcade game)">Star Wars</a>, <a href="/wiki/Firefox_(arcade_game)" class="mw-redirect" title="Firefox (arcade game)">Firefox</a>, <a href="/wiki/Star_Wars:_Return_of_the_Jedi_(arcade_game)" class="mw-redirect" title="Star Wars: Return of the Jedi (arcade game)">Return of the Jedi</a>, <a href="/wiki/Road_Runner_(video_game)" title="Road Runner (video game)">Road Runner</a>, <a href="/wiki/Star_Wars:_The_Empire_Strikes_Back_(arcade_game)" class="mw-redirect" title="Star Wars: The Empire Strikes Back (arcade game)">The Empire Strikes Back</a>, <a href="/wiki/Indiana_Jones_and_the_Temple_of_Doom_(arcade_game)" class="mw-redirect" title="Indiana Jones and the Temple of Doom (arcade game)">Indiana Jones and the Temple of Doom</a>, <a href="/wiki/720%C2%B0" title="720°">720°</a>, <a href="/wiki/Gauntlet_(arcade_game)" class="mw-redirect" title="Gauntlet (arcade game)">Gauntlet</a>, <a href="/wiki/Gauntlet_II" title="Gauntlet II">Gauntlet II</a>, <a href="/wiki/A.P.B._(video_game)" class="mw-redirect" title="A.P.B. (video game)">A.P.B.</a>, <a href="/wiki/Paperboy_(video_game)" title="Paperboy (video game)">Paperboy</a>, <a href="/wiki/RoadBlasters" title="RoadBlasters">RoadBlasters</a>, <a rel="nofollow" class="external text" href="http://www.arcade-museum.com/game_detail.php?game_id=10319">Vindicators Part II</a>, <a href="/wiki/Escape_from_the_Planet_of_the_Robot_Monsters" title="Escape from the Planet of the Robot Monsters">Escape from the Planet of the Robot Monsters</a>.</span> </li> <li id="cite_note-45"><span class="mw-cite-backlink"><b><a href="#cite_ref-45">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFJohn_Holmes_and_Wendy_Holmes2001" class="citation book cs1">John Holmes and Wendy Holmes (2001). <i>Speech Synthesis and Recognition</i> (2nd ed.). CRC. <a href="/wiki/ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <a href="/wiki/Special:BookSources/978-0-7484-0856-6" title="Special:BookSources/978-0-7484-0856-6"><bdi>978-0-7484-0856-6</bdi></a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.btitle=Speech+Synthesis+and+Recognition&rft.edition=2nd&rft.pub=CRC&rft.date=2001&rft.isbn=978-0-7484-0856-6&rft.au=John+Holmes+and+Wendy+Holmes&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-:0-46"><span class="mw-cite-backlink">^ <a href="#cite_ref-:0_46-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:0_46-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFLuceroSchoentgenBehlau2013" class="citation journal cs1">Lucero, J. C.; Schoentgen, J.; Behlau, M. (2013). <a rel="nofollow" class="external text" href="http://www.cic.unb.br/~lucero/papers/768_Paper.pdf">"Physics-based synthesis of disordered voices"</a> <span class="cs1-format">(PDF)</span>. <i>Interspeech 2013</i>. Lyon, France: International Speech Communication Association: 587–591. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.21437%2FInterspeech.2013-161">10.21437/Interspeech.2013-161</a>. <a href="/wiki/S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:17451802">17451802</a><span class="reference-accessdate">. Retrieved <span class="nowrap">Aug 27,</span> 2015</span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Interspeech+2013&rft.atitle=Physics-based+synthesis+of+disordered+voices&rft.pages=587-591&rft.date=2013&rft_id=info%3Adoi%2F10.21437%2FInterspeech.2013-161&rft_id=https%3A%2F%2Fapi.semanticscholar.org%2FCorpusID%3A17451802%23id-name%3DS2CID&rft.aulast=Lucero&rft.aufirst=J.+C.&rft.au=Schoentgen%2C+J.&rft.au=Behlau%2C+M.&rft_id=http%3A%2F%2Fwww.cic.unb.br%2F~lucero%2Fpapers%2F768_Paper.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-:1-47"><span class="mw-cite-backlink">^ <a href="#cite_ref-:1_47-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:1_47-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFEnglertMadazioGielowLucero2016" class="citation journal cs1">Englert, Marina; Madazio, Glaucya; Gielow, Ingrid; Lucero, Jorge; Behlau, Mara (2016). "Perceptual error identification of human and synthesized voices". <i>Journal of Voice</i>. <b>30</b> (5): 639.e17–639.e23. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1016%2Fj.jvoice.2015.07.017">10.1016/j.jvoice.2015.07.017</a>. <a href="/wiki/PMID_(identifier)" class="mw-redirect" title="PMID (identifier)">PMID</a> <a rel="nofollow" class="external text" href="https://pubmed.ncbi.nlm.nih.gov/26337775">26337775</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Journal+of+Voice&rft.atitle=Perceptual+error+identification+of+human+and+synthesized+voices&rft.volume=30&rft.issue=5&rft.pages=639.e17-639.e23&rft.date=2016&rft_id=info%3Adoi%2F10.1016%2Fj.jvoice.2015.07.017&rft_id=info%3Apmid%2F26337775&rft.aulast=Englert&rft.aufirst=Marina&rft.au=Madazio%2C+Glaucya&rft.au=Gielow%2C+Ingrid&rft.au=Lucero%2C+Jorge&rft.au=Behlau%2C+Mara&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-48"><span class="mw-cite-backlink"><b><a href="#cite_ref-48">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/20120213232606/http://hts.sp.nitech.ac.jp/">"The HMM-based Speech Synthesis System"</a>. Hts.sp.nitech.ac.j. Archived from <a rel="nofollow" class="external text" href="http://hts.sp.nitech.ac.jp/">the original</a> on 2012-02-13<span class="reference-accessdate">. Retrieved <span class="nowrap">2012-02-22</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=The+HMM-based+Speech+Synthesis+System&rft.pub=Hts.sp.nitech.ac.j&rft_id=http%3A%2F%2Fhts.sp.nitech.ac.jp%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-49"><span class="mw-cite-backlink"><b><a href="#cite_ref-49">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFRemezRubinPisoniCarrell1981" class="citation journal cs1">Remez, R.; Rubin, P.; Pisoni, D.; Carrell, T. (22 May 1981). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20111216113028/http://www.bsos.umd.edu/hesp/mwinn/Remez_et_al_1981.pdf">"Speech perception without traditional speech cues"</a> <span class="cs1-format">(PDF)</span>. <i>Science</i>. <b>212</b> (4497): 947–949. <a href="/wiki/Bibcode_(identifier)" class="mw-redirect" title="Bibcode (identifier)">Bibcode</a>:<a rel="nofollow" class="external text" href="https://ui.adsabs.harvard.edu/abs/1981Sci...212..947R">1981Sci...212..947R</a>. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1126%2Fscience.7233191">10.1126/science.7233191</a>. <a href="/wiki/PMID_(identifier)" class="mw-redirect" title="PMID (identifier)">PMID</a> <a rel="nofollow" class="external text" href="https://pubmed.ncbi.nlm.nih.gov/7233191">7233191</a>. Archived from <a rel="nofollow" class="external text" href="http://www.bsos.umd.edu/hesp/mwinn/Remez_et_al_1981.pdf">the original</a> <span class="cs1-format">(PDF)</span> on 2011-12-16<span class="reference-accessdate">. Retrieved <span class="nowrap">2011-12-14</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Science&rft.atitle=Speech+perception+without+traditional+speech+cues&rft.volume=212&rft.issue=4497&rft.pages=947-949&rft.date=1981-05-22&rft_id=info%3Apmid%2F7233191&rft_id=info%3Adoi%2F10.1126%2Fscience.7233191&rft_id=info%3Abibcode%2F1981Sci...212..947R&rft.aulast=Remez&rft.aufirst=R.&rft.au=Rubin%2C+P.&rft.au=Pisoni%2C+D.&rft.au=Carrell%2C+T.&rft_id=http%3A%2F%2Fwww.bsos.umd.edu%2Fhesp%2Fmwinn%2FRemez_et_al_1981.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-arxivmello-50"><span class="mw-cite-backlink"><b><a href="#cite_ref-arxivmello_50-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFValle2020" class="citation arxiv cs1">Valle, Rafael (2020). "Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens". <a href="/wiki/ArXiv_(identifier)" class="mw-redirect" title="ArXiv (identifier)">arXiv</a>:<span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://arxiv.org/abs/1910.11997">1910.11997</a></span> [<a rel="nofollow" class="external text" href="https://arxiv.org/archive/eess">eess</a>].</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=preprint&rft.jtitle=arXiv&rft.atitle=Mellotron%3A+Multispeaker+expressive+voice+synthesis+by+conditioning+on+rhythm%2C+pitch+and+global+style+tokens&rft.date=2020&rft_id=info%3Aarxiv%2F1910.11997&rft.aulast=Valle&rft.aufirst=Rafael&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-automaton2-51"><span class="mw-cite-backlink">^ <a href="#cite_ref-automaton2_51-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-automaton2_51-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFKurosawa2021" class="citation web cs1">Kurosawa, Yuki (2021-01-19). <a rel="nofollow" class="external text" href="https://automaton-media.com/articles/newsjp/20210119-149494/">"ゲームキャラ音声読み上げソフト「15.ai」公開中。『Undertale』や『Portal』のキャラに好きなセリフを言ってもらえる"</a>. <i>AUTOMATON</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20210119103031/https://automaton-media.com/articles/newsjp/20210119-149494/">Archived</a> from the original on 2021-01-19<span class="reference-accessdate">. Retrieved <span class="nowrap">2021-01-19</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=AUTOMATON&rft.atitle=%E3%82%B2%E3%83%BC%E3%83%A0%E3%82%AD%E3%83%A3%E3%83%A9%E9%9F%B3%E5%A3%B0%E8%AA%AD%E3%81%BF%E4%B8%8A%E3%81%92%E3%82%BD%E3%83%95%E3%83%88%E3%80%8C15.ai%E3%80%8D%E5%85%AC%E9%96%8B%E4%B8%AD%E3%80%82%E3%80%8EUndertale%E3%80%8F%E3%82%84%E3%80%8EPortal%E3%80%8F%E3%81%AE%E3%82%AD%E3%83%A3%E3%83%A9%E3%81%AB%E5%A5%BD%E3%81%8D%E3%81%AA%E3%82%BB%E3%83%AA%E3%83%95%E3%82%92%E8%A8%80%E3%81%A3%E3%81%A6%E3%82%82%E3%82%89%E3%81%88%E3%82%8B&rft.date=2021-01-19&rft.aulast=Kurosawa&rft.aufirst=Yuki&rft_id=https%3A%2F%2Fautomaton-media.com%2Farticles%2Fnewsjp%2F20210119-149494%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-Denfaminicogamer2-52"><span class="mw-cite-backlink">^ <a href="#cite_ref-Denfaminicogamer2_52-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-Denfaminicogamer2_52-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFYoshiyuki2021" class="citation web cs1">Yoshiyuki, Furushima (2021-01-18). <a rel="nofollow" class="external text" href="https://news.denfaminicogamer.jp/news/210118f">"『Portal』のGLaDOSや『UNDERTALE』のサンズがテキストを読み上げてくれる。文章に込められた感情まで再現することを目指すサービス「15.ai」が話題に"</a>. <i>Denfaminicogamer</i>. <a rel="nofollow" class="external text" href="https://web.archive.org/web/20210118051321/https://news.denfaminicogamer.jp/news/210118f">Archived</a> from the original on 2021-01-18<span class="reference-accessdate">. Retrieved <span class="nowrap">2021-01-18</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=Denfaminicogamer&rft.atitle=%E3%80%8EPortal%E3%80%8F%E3%81%AEGLaDOS%E3%82%84%E3%80%8EUNDERTALE%E3%80%8F%E3%81%AE%E3%82%B5%E3%83%B3%E3%82%BA%E3%81%8C%E3%83%86%E3%82%AD%E3%82%B9%E3%83%88%E3%82%92%E8%AA%AD%E3%81%BF%E4%B8%8A%E3%81%92%E3%81%A6%E3%81%8F%E3%82%8C%E3%82%8B%E3%80%82%E6%96%87%E7%AB%A0%E3%81%AB%E8%BE%BC%E3%82%81%E3%82%89%E3%82%8C%E3%81%9F%E6%84%9F%E6%83%85%E3%81%BE%E3%81%A7%E5%86%8D%E7%8F%BE%E3%81%99%E3%82%8B%E3%81%93%E3%81%A8%E3%82%92%E7%9B%AE%E6%8C%87%E3%81%99%E3%82%B5%E3%83%BC%E3%83%93%E3%82%B9%E3%80%8C15.ai%E3%80%8D%E3%81%8C%E8%A9%B1%E9%A1%8C%E3%81%AB&rft.date=2021-01-18&rft.aulast=Yoshiyuki&rft.aufirst=Furushima&rft_id=https%3A%2F%2Fnews.denfaminicogamer.jp%2Fnews%2F210118f&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-53"><span class="mw-cite-backlink"><b><a href="#cite_ref-53">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://sifted.eu/articles/generative-ai-audio-elevenlabs/">"Generative AI comes for cinema dubbing: Audio AI startup ElevenLabs raises pre-seed"</a>. <i>Sifted</i>. January 23, 2023<span class="reference-accessdate">. Retrieved <span class="nowrap">2023-02-03</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=Sifted&rft.atitle=Generative+AI+comes+for+cinema+dubbing%3A+Audio+AI+startup+ElevenLabs+raises+pre-seed&rft.date=2023-01-23&rft_id=https%3A%2F%2Fsifted.eu%2Farticles%2Fgenerative-ai-audio-elevenlabs%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-:13-54"><span class="mw-cite-backlink">^ <a href="#cite_ref-:13_54-0"><sup><i><b>a</b></i></sup></a> <a href="#cite_ref-:13_54-1"><sup><i><b>b</b></i></sup></a></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFAshworth2023" class="citation magazine cs1">Ashworth, Boone (April 12, 2023). <a rel="nofollow" class="external text" href="https://www.wired.com/story/ai-podcasts-podcastle-revoice-descript/">"AI Can Clone Your Favorite Podcast Host's Voice"</a>. <i>Wired</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2023-04-25</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Wired&rft.atitle=AI+Can+Clone+Your+Favorite+Podcast+Host%27s+Voice&rft.date=2023-04-12&rft.aulast=Ashworth&rft.aufirst=Boone&rft_id=https%3A%2F%2Fwww.wired.com%2Fstory%2Fai-podcasts-podcastle-revoice-descript%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-55"><span class="mw-cite-backlink"><b><a href="#cite_ref-55">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFWIRED_Staff" class="citation magazine cs1">WIRED Staff. <a rel="nofollow" class="external text" href="https://www.wired.com/story/gadget-lab-podcast-594/">"This Podcast Is Not Hosted by AI Voice Clones. We Swear"</a>. <i>Wired</i>. <a href="/wiki/ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/1059-1028">1059-1028</a><span class="reference-accessdate">. Retrieved <span class="nowrap">2023-07-25</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Wired&rft.atitle=This+Podcast+Is+Not+Hosted+by+AI+Voice+Clones.+We+Swear&rft.issn=1059-1028&rft.au=WIRED+Staff&rft_id=https%3A%2F%2Fwww.wired.com%2Fstory%2Fgadget-lab-podcast-594%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-:34-56"><span class="mw-cite-backlink"><b><a href="#cite_ref-:34_56-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFWiggers2023" class="citation web cs1">Wiggers, Kyle (2023-06-20). <a rel="nofollow" class="external text" href="https://techcrunch.com/2023/06/20/voice-generating-platform-elevenlabs-raises-19m-launches-detection-tool/">"Voice-generating platform ElevenLabs raises $19M, launches detection tool"</a>. <i>TechCrunch</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2023-07-25</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=TechCrunch&rft.atitle=Voice-generating+platform+ElevenLabs+raises+%2419M%2C+launches+detection+tool&rft.date=2023-06-20&rft.aulast=Wiggers&rft.aufirst=Kyle&rft_id=https%3A%2F%2Ftechcrunch.com%2F2023%2F06%2F20%2Fvoice-generating-platform-elevenlabs-raises-19m-launches-detection-tool%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-57"><span class="mw-cite-backlink"><b><a href="#cite_ref-57">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFBonk" class="citation web cs1">Bonk, Lawrence. <a rel="nofollow" class="external text" href="https://www.lifewire.com/elevenlabs-new-audiobook-ai-tool-7550061">"ElevenLabs' Powerful New AI Tool Lets You Make a Full Audiobook in Minutes"</a>. <i>Lifewire</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2023-07-25</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=Lifewire&rft.atitle=ElevenLabs%27+Powerful+New+AI+Tool+Lets+You+Make+a+Full+Audiobook+in+Minutes&rft.aulast=Bonk&rft.aufirst=Lawrence&rft_id=https%3A%2F%2Fwww.lifewire.com%2Felevenlabs-new-audiobook-ai-tool-7550061&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-58"><span class="mw-cite-backlink"><b><a href="#cite_ref-58">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFZhu2020" class="citation journal cs1">Zhu, Jian (2020-05-25). <a rel="nofollow" class="external text" href="https://dx.doi.org/10.21437/speechprosody.2020-190">"Probing the phonetic and phonological knowledge of tones in Mandarin TTS models"</a>. <i>Speech Prosody 2020</i>. ISCA: ISCA: 930–934. <a href="/wiki/ArXiv_(identifier)" class="mw-redirect" title="ArXiv (identifier)">arXiv</a>:<span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://arxiv.org/abs/1912.10915">1912.10915</a></span>. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.21437%2Fspeechprosody.2020-190">10.21437/speechprosody.2020-190</a>. <a href="/wiki/S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:209444942">209444942</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Speech+Prosody+2020&rft.atitle=Probing+the+phonetic+and+phonological+knowledge+of+tones+in+Mandarin+TTS+models&rft.pages=930-934&rft.date=2020-05-25&rft_id=info%3Aarxiv%2F1912.10915&rft_id=https%3A%2F%2Fapi.semanticscholar.org%2FCorpusID%3A209444942%23id-name%3DS2CID&rft_id=info%3Adoi%2F10.21437%2Fspeechprosody.2020-190&rft.aulast=Zhu&rft.aufirst=Jian&rft_id=http%3A%2F%2Fdx.doi.org%2F10.21437%2Fspeechprosody.2020-190&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-59"><span class="mw-cite-backlink"><b><a href="#cite_ref-59">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFSmithMansted2020" class="citation book cs1">Smith, Hannah; Mansted, Katherine (April 1, 2020). <i>Weaponised deep fakes: National security and democracy</i>. Vol. 28. <a href="/wiki/Australian_Strategic_Policy_Institute" title="Australian Strategic Policy Institute">Australian Strategic Policy Institute</a>. pp. 11–13. <a href="/wiki/ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/2209-9689">2209-9689</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.btitle=Weaponised+deep+fakes%3A+National+security+and+democracy&rft.pages=11-13&rft.pub=Australian+Strategic+Policy+Institute&rft.date=2020-04-01&rft.issn=2209-9689&rft.aulast=Smith&rft.aufirst=Hannah&rft.au=Mansted%2C+Katherine&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span><span class="cs1-maint citation-comment"><code class="cs1-code">{{<a href="/wiki/Template:Cite_book" title="Template:Cite book">cite book</a>}}</code>: CS1 maint: date and year (<a href="/wiki/Category:CS1_maint:_date_and_year" title="Category:CS1 maint: date and year">link</a>)</span></span> </li> <li id="cite_note-60"><span class="mw-cite-backlink"><b><a href="#cite_ref-60">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFLyu2020" class="citation book cs1">Lyu, Siwei (2020). <a rel="nofollow" class="external text" href="https://ieeexplore.ieee.org/document/9105991">"Deepfake Detection: Current Challenges and Next Steps"</a>. <i>2020 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)</i>. pp. 1–6. <a href="/wiki/ArXiv_(identifier)" class="mw-redirect" title="ArXiv (identifier)">arXiv</a>:<span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://arxiv.org/abs/2003.09234">2003.09234</a></span>. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1109%2Ficmew46912.2020.9105991">10.1109/icmew46912.2020.9105991</a>. <a href="/wiki/ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <a href="/wiki/Special:BookSources/978-1-7281-1485-9" title="Special:BookSources/978-1-7281-1485-9"><bdi>978-1-7281-1485-9</bdi></a>. <a href="/wiki/S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:214605906">214605906</a><span class="reference-accessdate">. Retrieved <span class="nowrap">2022-06-29</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=bookitem&rft.atitle=Deepfake+Detection%3A+Current+Challenges+and+Next+Steps&rft.btitle=2020+IEEE+International+Conference+on+Multimedia+%26+Expo+Workshops+%28ICMEW%29&rft.pages=1-6&rft.date=2020&rft_id=info%3Aarxiv%2F2003.09234&rft_id=https%3A%2F%2Fapi.semanticscholar.org%2FCorpusID%3A214605906%23id-name%3DS2CID&rft_id=info%3Adoi%2F10.1109%2Ficmew46912.2020.9105991&rft.isbn=978-1-7281-1485-9&rft.aulast=Lyu&rft.aufirst=Siwei&rft_id=https%3A%2F%2Fieeexplore.ieee.org%2Fdocument%2F9105991&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-Audio_deepfake_:0-61"><span class="mw-cite-backlink"><b><a href="#cite_ref-Audio_deepfake_:0_61-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFDiakopoulosJohnson2020" class="citation journal cs1">Diakopoulos, Nicholas; Johnson, Deborah (June 2020). <a rel="nofollow" class="external text" href="http://journals.sagepub.com/doi/10.1177/1461444820925811">"Anticipating and addressing the ethical implications of deepfakes in the context of elections"</a>. <i>New Media & Society</i>. <b>23</b> (7) (published 2020-06-05): 2072–2098. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1177%2F1461444820925811">10.1177/1461444820925811</a>. <a href="/wiki/ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/1461-4448">1461-4448</a>. <a href="/wiki/S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:226196422">226196422</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=New+Media+%26+Society&rft.atitle=Anticipating+and+addressing+the+ethical+implications+of+deepfakes+in+the+context+of+elections&rft.volume=23&rft.issue=7&rft.pages=2072-2098&rft.date=2020-06&rft_id=https%3A%2F%2Fapi.semanticscholar.org%2FCorpusID%3A226196422%23id-name%3DS2CID&rft.issn=1461-4448&rft_id=info%3Adoi%2F10.1177%2F1461444820925811&rft.aulast=Diakopoulos&rft.aufirst=Nicholas&rft.au=Johnson%2C+Deborah&rft_id=http%3A%2F%2Fjournals.sagepub.com%2Fdoi%2F10.1177%2F1461444820925811&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-62"><span class="mw-cite-backlink"><b><a href="#cite_ref-62">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFMurphy2024" class="citation web cs1">Murphy, Margi (20 February 2024). <a rel="nofollow" class="external text" href="https://www.bloomberg.com/news/articles/2024-02-21/biden-deepfake-and-other-audio-fakes-were-made-with-elevenlabs-ai">"Deepfake Audio Boom Exploits One Billion-Dollar Startup's AI"</a>. Bloomberg.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=Deepfake+Audio+Boom+Exploits+One+Billion-Dollar+Startup%27s+AI&rft.pub=Bloomberg&rft.date=2024-02-20&rft.aulast=Murphy&rft.aufirst=Margi&rft_id=https%3A%2F%2Fwww.bloomberg.com%2Fnews%2Farticles%2F2024-02-21%2Fbiden-deepfake-and-other-audio-fakes-were-made-with-elevenlabs-ai&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-Audio_deepfake_:10-63"><span class="mw-cite-backlink"><b><a href="#cite_ref-Audio_deepfake_:10_63-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFChadhaKumarKashyapGupta2021" class="citation cs2">Chadha, Anupama; Kumar, Vaibhav; Kashyap, Sonu; Gupta, Mayank (2021), Singh, Pradeep Kumar; Wierzchoń, Sławomir T.; Tanwar, Sudeep; Ganzha, Maria (eds.), <a rel="nofollow" class="external text" href="https://link.springer.com/10.1007/978-981-16-0733-2_39">"Deepfake: An Overview"</a>, <i>Proceedings of Second International Conference on Computing, Communications, and Cyber-Security</i>, Lecture Notes in Networks and Systems, vol. 203, Singapore: Springer Singapore, pp. 557–566, <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1007%2F978-981-16-0733-2_39">10.1007/978-981-16-0733-2_39</a>, <a href="/wiki/ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <a href="/wiki/Special:BookSources/978-981-16-0732-5" title="Special:BookSources/978-981-16-0732-5"><bdi>978-981-16-0732-5</bdi></a>, <a href="/wiki/S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:236666289">236666289</a><span class="reference-accessdate">, retrieved <span class="nowrap">2022-06-29</span></span></cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Proceedings+of+Second+International+Conference+on+Computing%2C+Communications%2C+and+Cyber-Security&rft.atitle=Deepfake%3A+An+Overview&rft.volume=203&rft.pages=557-566&rft.date=2021&rft_id=https%3A%2F%2Fapi.semanticscholar.org%2FCorpusID%3A236666289%23id-name%3DS2CID&rft_id=info%3Adoi%2F10.1007%2F978-981-16-0733-2_39&rft.isbn=978-981-16-0732-5&rft.aulast=Chadha&rft.aufirst=Anupama&rft.au=Kumar%2C+Vaibhav&rft.au=Kashyap%2C+Sonu&rft.au=Gupta%2C+Mayank&rft_id=https%3A%2F%2Flink.springer.com%2F10.1007%2F978-981-16-0733-2_39&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-Audio_deepfake_:11-64"><span class="mw-cite-backlink"><b><a href="#cite_ref-Audio_deepfake_:11_64-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation news cs1"><a rel="nofollow" class="external text" href="https://www.washingtonpost.com/technology/2021/08/18/val-kilmer-ai-voice-cloning/">"AI gave Val Kilmer his voice back. But critics worry the technology could be misused"</a>. <i>Washington Post</i>. <a href="/wiki/ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/0190-8286">0190-8286</a><span class="reference-accessdate">. Retrieved <span class="nowrap">2022-06-29</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Washington+Post&rft.atitle=AI+gave+Val+Kilmer+his+voice+back.+But+critics+worry+the+technology+could+be+misused.&rft.issn=0190-8286&rft_id=https%3A%2F%2Fwww.washingtonpost.com%2Ftechnology%2F2021%2F08%2F18%2Fval-kilmer-ai-voice-cloning%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-65"><span class="mw-cite-backlink"><b><a href="#cite_ref-65">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFEtienne2021" class="citation web cs1">Etienne, Vanessa (August 19, 2021). <a rel="nofollow" class="external text" href="https://people.com/movies/val-kilmer-gets-his-voice-back-after-throat-cancer-battle-using-ai-technology-hear-the-results/">"Val Kilmer Gets His Voice Back After Throat Cancer Battle Using AI Technology: Hear the Results"</a>. <i>PEOPLE.com</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2022-07-01</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=PEOPLE.com&rft.atitle=Val+Kilmer+Gets+His+Voice+Back+After+Throat+Cancer+Battle+Using+AI+Technology%3A+Hear+the+Results&rft.date=2021-08-19&rft.aulast=Etienne&rft.aufirst=Vanessa&rft_id=https%3A%2F%2Fpeople.com%2Fmovies%2Fval-kilmer-gets-his-voice-back-after-throat-cancer-battle-using-ai-technology-hear-the-results%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-66"><span class="mw-cite-backlink"><b><a href="#cite_ref-66">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFNewman" class="citation magazine cs1">Newman, Lily Hay. <a rel="nofollow" class="external text" href="https://www.wired.com/story/ai-voice-deep-fakes/">"AI-Generated Voice Deepfakes Aren't Scary Good—Yet"</a>. <i>Wired</i>. <a href="/wiki/ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/1059-1028">1059-1028</a><span class="reference-accessdate">. Retrieved <span class="nowrap">2023-07-25</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Wired&rft.atitle=AI-Generated+Voice+Deepfakes+Aren%27t+Scary+Good%E2%80%94Yet&rft.issn=1059-1028&rft.aulast=Newman&rft.aufirst=Lily+Hay&rft_id=https%3A%2F%2Fwww.wired.com%2Fstory%2Fai-voice-deep-fakes%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-67"><span class="mw-cite-backlink"><b><a href="#cite_ref-67">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://www.w3.org/TR/speech-synthesis/#S3.1.8">"Speech synthesis"</a>. World Wide Web Organization.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=Speech+synthesis&rft.pub=World+Wide+Web+Organization&rft_id=http%3A%2F%2Fwww.w3.org%2FTR%2Fspeech-synthesis%2F%23S3.1.8&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-68"><span class="mw-cite-backlink"><b><a href="#cite_ref-68">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://festvox.org/blizzard">"Blizzard Challenge"</a>. Festvox.org<span class="reference-accessdate">. Retrieved <span class="nowrap">2012-02-22</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=Blizzard+Challenge&rft.pub=Festvox.org&rft_id=http%3A%2F%2Ffestvox.org%2Fblizzard&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-69"><span class="mw-cite-backlink"><b><a href="#cite_ref-69">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation news cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/20080517102201/http://www.port.ac.uk/aboutus/newsandevents/news/title%2C74220%2Cen.html">"Smile -and the world can hear you"</a>. University of Portsmouth. January 9, 2008. Archived from <a rel="nofollow" class="external text" href="http://www.port.ac.uk/aboutus/newsandevents/news/title,74220,en.html">the original</a> on May 17, 2008.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Smile+-and+the+world+can+hear+you&rft.date=2008-01-09&rft_id=http%3A%2F%2Fwww.port.ac.uk%2Faboutus%2Fnewsandevents%2Fnews%2Ftitle%2C74220%2Cen.html&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-70"><span class="mw-cite-backlink"><b><a href="#cite_ref-70">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation news cs1"><a rel="nofollow" class="external text" href="https://www.sciencedaily.com/releases/2008/01/080111224745.htm">"Smile – And The World Can Hear You, Even If You Hide"</a>. <i>Science Daily</i>. January 2008.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Science+Daily&rft.atitle=Smile+%E2%80%93+And+The+World+Can+Hear+You%2C+Even+If+You+Hide&rft.date=2008-01&rft_id=https%3A%2F%2Fwww.sciencedaily.com%2Freleases%2F2008%2F01%2F080111224745.htm&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-71"><span class="mw-cite-backlink"><b><a href="#cite_ref-71">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFDrahota2008" class="citation journal cs1">Drahota, A. (2008). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20130703062330/https://peer.ccsd.cnrs.fr/docs/00/49/91/97/PDF/PEER_stage2_10.1016/j.specom.2007.10.001.pdf">"The vocal communication of different kinds of smile"</a> <span class="cs1-format">(PDF)</span>. <i>Speech Communication</i>. <b>50</b> (4): 278–287. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1016%2Fj.specom.2007.10.001">10.1016/j.specom.2007.10.001</a>. <a href="/wiki/S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:46693018">46693018</a>. Archived from <a rel="nofollow" class="external text" href="http://peer.ccsd.cnrs.fr/docs/00/49/91/97/PDF/PEER_stage2_10.1016%252Fj.specom.2007.10.001.pdf">the original</a> <span class="cs1-format">(PDF)</span> on 2013-07-03.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Speech+Communication&rft.atitle=The+vocal+communication+of+different+kinds+of+smile&rft.volume=50&rft.issue=4&rft.pages=278-287&rft.date=2008&rft_id=info%3Adoi%2F10.1016%2Fj.specom.2007.10.001&rft_id=https%3A%2F%2Fapi.semanticscholar.org%2FCorpusID%3A46693018%23id-name%3DS2CID&rft.aulast=Drahota&rft.aufirst=A.&rft_id=http%3A%2F%2Fpeer.ccsd.cnrs.fr%2Fdocs%2F00%2F49%2F91%2F97%2FPDF%2FPEER_stage2_10.1016%25252Fj.specom.2007.10.001.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-72"><span class="mw-cite-backlink"><b><a href="#cite_ref-72">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFPrathoshRamakrishnanAnanthapadmanabha2013" class="citation journal cs1">Prathosh, A. P.; Ramakrishnan, A. G.; Ananthapadmanabha, T. V. (December 2013). "Epoch extraction based on integrated linear prediction residual using plosion index". <i>IEEE Trans. Audio Speech Language Processing</i>. <b>21</b> (12): 2471–2480. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1109%2FTASL.2013.2273717">10.1109/TASL.2013.2273717</a>. <a href="/wiki/S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:10491251">10491251</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=IEEE+Trans.+Audio+Speech+Language+Processing&rft.atitle=Epoch+extraction+based+on+integrated+linear+prediction+residual+using+plosion+index&rft.volume=21&rft.issue=12&rft.pages=2471-2480&rft.date=2013-12&rft_id=info%3Adoi%2F10.1109%2FTASL.2013.2273717&rft_id=https%3A%2F%2Fapi.semanticscholar.org%2FCorpusID%3A10491251%23id-name%3DS2CID&rft.aulast=Prathosh&rft.aufirst=A.+P.&rft.au=Ramakrishnan%2C+A.+G.&rft.au=Ananthapadmanabha%2C+T.+V.&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-TI_will_exit_dedicated_speech-synthesis_chips,_transfer_products_to_Sensory-73"><span class="mw-cite-backlink"><b><a href="#cite_ref-TI_will_exit_dedicated_speech-synthesis_chips,_transfer_products_to_Sensory_73-0">^</a></b></span> <span class="reference-text">EE Times. "<a rel="nofollow" class="external text" href="http://www.eetimes.com/electronics-news/4102385/TI-will-exit-dedicated-speech-synthesis-chips-transfer-products-to-Sensory">TI will exit dedicated speech-synthesis chips, transfer products to Sensory</a> <a rel="nofollow" class="external text" href="https://web.archive.org/web/20120528014257/http://www.eetimes.com/electronics-news/4102385/TI-will-exit-dedicated-speech-synthesis-chips-transfer-products-to-Sensory">Archived</a> 2012-05-28 at the <a href="/wiki/Wayback_Machine" title="Wayback Machine">Wayback Machine</a>." June 14, 2001.</span> </li> <li id="cite_note-74"><span class="mw-cite-backlink"><b><a href="#cite_ref-74">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/20120324014644/http://www.atarimuseum.com/ahs_archives/archives/pdf/computers/8bits/1400xlmodem.pdf">"1400XL/1450XL Speech Handler External Reference Specification"</a> <span class="cs1-format">(PDF)</span>. Archived from <a rel="nofollow" class="external text" href="http://www.atarimuseum.com/ahs_archives/archives/pdf/computers/8bits/1400xlmodem.pdf">the original</a> <span class="cs1-format">(PDF)</span> on 2012-03-24<span class="reference-accessdate">. Retrieved <span class="nowrap">2012-02-22</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=1400XL%2F1450XL+Speech+Handler+External+Reference+Specification&rft_id=http%3A%2F%2Fwww.atarimuseum.com%2Fahs_archives%2Farchives%2Fpdf%2Fcomputers%2F8bits%2F1400xlmodem.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-demo-75"><span class="mw-cite-backlink"><b><a href="#cite_ref-demo_75-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://www.folklore.org/StoryView.py?story=Intro_Demo.txt">"It Sure Is Great To Get Out Of That Bag!"</a>. folklore.org<span class="reference-accessdate">. Retrieved <span class="nowrap">2013-03-24</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=It+Sure+Is+Great+To+Get+Out+Of+That+Bag%21&rft.pub=folklore.org&rft_id=http%3A%2F%2Fwww.folklore.org%2FStoryView.py%3Fstory%3DIntro_Demo.txt&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-76"><span class="mw-cite-backlink"><b><a href="#cite_ref-76">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://aws.amazon.com/polly/">"Amazon Polly"</a>. <i>Amazon Web Services, Inc</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2020-04-28</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=Amazon+Web+Services%2C+Inc.&rft.atitle=Amazon+Polly&rft_id=https%3A%2F%2Faws.amazon.com%2Fpolly%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-77"><span class="mw-cite-backlink"><b><a href="#cite_ref-77">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFMiner,_Jay1991" class="citation book cs1"><a href="/wiki/Jay_Miner" title="Jay Miner">Miner, Jay</a>; et al. (1991). <i>Amiga Hardware Reference Manual</i> (3rd ed.). <a href="/wiki/Addison-Wesley" title="Addison-Wesley">Addison-Wesley</a> Publishing Company, Inc. <a href="/wiki/ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <a href="/wiki/Special:BookSources/978-0-201-56776-2" title="Special:BookSources/978-0-201-56776-2"><bdi>978-0-201-56776-2</bdi></a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.btitle=Amiga+Hardware+Reference+Manual&rft.edition=3rd&rft.pub=Addison-Wesley+Publishing+Company%2C+Inc.&rft.date=1991&rft.isbn=978-0-201-56776-2&rft.au=Miner%2C+Jay&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-78"><span class="mw-cite-backlink"><b><a href="#cite_ref-78">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFDevitt1995" class="citation web cs1">Devitt, Francesco (30 June 1995). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20120226143859/https://uk.aminet.net/util/libs/translator42.readme">"Translator Library (Multilingual-speech version)"</a>. Archived from <a rel="nofollow" class="external text" href="http://uk.aminet.net/util/libs/translator42.readme">the original</a> on 26 February 2012<span class="reference-accessdate">. Retrieved <span class="nowrap">9 April</span> 2013</span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=Translator+Library+%28Multilingual-speech+version%29&rft.date=1995-06-30&rft.aulast=Devitt&rft.aufirst=Francesco&rft_id=http%3A%2F%2Fuk.aminet.net%2Futil%2Flibs%2Ftranslator42.readme&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-Narrator-79"><span class="mw-cite-backlink"><b><a href="#cite_ref-Narrator_79-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/20030621002716/http://www.microsoft.com/enable/training/windowsxp/usingnarrator.aspx">"Accessibility Tutorials for Windows XP: Using Narrator"</a>. Microsoft. 2011-01-29. Archived from <a rel="nofollow" class="external text" href="http://www.microsoft.com/enable/training/windowsxp/usingnarrator.aspx">the original</a> on June 21, 2003<span class="reference-accessdate">. Retrieved <span class="nowrap">2011-01-29</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=Accessibility+Tutorials+for+Windows+XP%3A+Using+Narrator&rft.pub=Microsoft&rft.date=2011-01-29&rft_id=http%3A%2F%2Fwww.microsoft.com%2Fenable%2Ftraining%2Fwindowsxp%2Fusingnarrator.aspx&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-microsoft.com-80"><span class="mw-cite-backlink"><b><a href="#cite_ref-microsoft.com_80-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://support.microsoft.com/kb/306902">"How to configure and use Text-to-Speech in Windows XP and in Windows Vista"</a>. Microsoft. 2007-05-07<span class="reference-accessdate">. Retrieved <span class="nowrap">2010-02-17</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=How+to+configure+and+use+Text-to-Speech+in+Windows+XP+and+in+Windows+Vista&rft.pub=Microsoft&rft.date=2007-05-07&rft_id=http%3A%2F%2Fsupport.microsoft.com%2Fkb%2F306902&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-81"><span class="mw-cite-backlink"><b><a href="#cite_ref-81">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFJean-Michel_Trivi2009" class="citation web cs1">Jean-Michel Trivi (2009-09-23). <a rel="nofollow" class="external text" href="http://android-developers.blogspot.com/2009/09/introduction-to-text-to-speech-in.html">"An introduction to Text-To-Speech in Android"</a>. Android-developers.blogspot.com<span class="reference-accessdate">. Retrieved <span class="nowrap">2010-02-17</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=An+introduction+to+Text-To-Speech+in+Android&rft.pub=Android-developers.blogspot.com&rft.date=2009-09-23&rft.au=Jean-Michel+Trivi&rft_id=http%3A%2F%2Fandroid-developers.blogspot.com%2F2009%2F09%2Fintroduction-to-text-to-speech-in.html&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-82"><span class="mw-cite-backlink"><b><a href="#cite_ref-82">^</a></b></span> <span class="reference-text">Andreas Bischoff, <a rel="nofollow" class="external text" href="http://www.dr-bischoff.de/research/pdf/bischoff_pediaphon_uwsi2007_final.pdf">The Pediaphon – Speech Interface to the free Wikipedia Encyclopedia for Mobile Phones</a>, PDA's and MP3-Players, Proceedings of the 18th International Conference on Database and Expert Systems Applications, Pages: 575–579 <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><a href="/wiki/ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <a href="/wiki/Special:BookSources/0-7695-2932-1" title="Special:BookSources/0-7695-2932-1">0-7695-2932-1</a>, 2007</span> </li> <li id="cite_note-83"><span class="mw-cite-backlink"><b><a href="#cite_ref-83">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.gnu.org/software/gnuspeech/">"gnuspeech"</a>. Gnu.org<span class="reference-accessdate">. Retrieved <span class="nowrap">2010-02-17</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=gnuspeech&rft.pub=Gnu.org&rft_id=https%3A%2F%2Fwww.gnu.org%2Fsoftware%2Fgnuspeech%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-84"><span class="mw-cite-backlink"><b><a href="#cite_ref-84">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/20131003104852/http://amhistory.si.edu/archives/speechsynthesis/ss_home.htm">"Smithsonian Speech Synthesis History Project (SSSHP) 1986–2002"</a>. Mindspring.com. Archived from <a rel="nofollow" class="external text" href="http://www.mindspring.com/~ssshp/ssshp_cd/ss_home.htm">the original</a> on 2013-10-03<span class="reference-accessdate">. Retrieved <span class="nowrap">2010-02-17</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=Smithsonian+Speech+Synthesis+History+Project+%28SSSHP%29+1986%E2%80%932002&rft.pub=Mindspring.com&rft_id=http%3A%2F%2Fwww.mindspring.com%2F~ssshp%2Fssshp_cd%2Fss_home.htm&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-GoogleLearningTransferToTTS2018-85"><span class="mw-cite-backlink"><b><a href="#cite_ref-GoogleLearningTransferToTTS2018_85-0">^</a></b></span> <span class="reference-text"> <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFJiaZhangWeiss2018" class="citation cs2">Jia, Ye; Zhang, Yu; Weiss, Ron J. (2018-06-12), "Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis", <i><a href="/wiki/Advances_in_Neural_Information_Processing_Systems" class="mw-redirect" title="Advances in Neural Information Processing Systems">Advances in Neural Information Processing Systems</a></i>, <b>31</b>: 4485–4495, <a href="/wiki/ArXiv_(identifier)" class="mw-redirect" title="ArXiv (identifier)">arXiv</a>:<span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://arxiv.org/abs/1806.04558">1806.04558</a></span></cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Advances+in+Neural+Information+Processing+Systems&rft.atitle=Transfer+Learning+from+Speaker+Verification+to+Multispeaker+Text-To-Speech+Synthesis&rft.volume=31&rft.pages=4485-4495&rft.date=2018-06-12&rft_id=info%3Aarxiv%2F1806.04558&rft.aulast=Jia&rft.aufirst=Ye&rft.au=Zhang%2C+Yu&rft.au=Weiss%2C+Ron+J.&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-Baidu2018-86"><span class="mw-cite-backlink"><b><a href="#cite_ref-Baidu2018_86-0">^</a></b></span> <span class="reference-text"> <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFArıkChenPengPing2018" class="citation cs2">Arık, Sercan Ö.; Chen, Jitong; Peng, Kainan; Ping, Wei; Zhou, Yanqi (2018), <a rel="nofollow" class="external text" href="http://papers.nips.cc/paper/8206-neural-voice-cloning-with-a-few-samples">"Neural Voice Cloning with a Few Samples"</a>, <i><a href="/wiki/Advances_in_Neural_Information_Processing_Systems" class="mw-redirect" title="Advances in Neural Information Processing Systems">Advances in Neural Information Processing Systems</a></i>, <b>31</b>, <a href="/wiki/ArXiv_(identifier)" class="mw-redirect" title="ArXiv (identifier)">arXiv</a>:<span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://arxiv.org/abs/1802.06006">1802.06006</a></span></cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Advances+in+Neural+Information+Processing+Systems&rft.atitle=Neural+Voice+Cloning+with+a+Few+Samples&rft.volume=31&rft.date=2018&rft_id=info%3Aarxiv%2F1802.06006&rft.aulast=Ar%C4%B1k&rft.aufirst=Sercan+%C3%96.&rft.au=Chen%2C+Jitong&rft.au=Peng%2C+Kainan&rft.au=Ping%2C+Wei&rft.au=Zhou%2C+Yanqi&rft_id=http%3A%2F%2Fpapers.nips.cc%2Fpaper%2F8206-neural-voice-cloning-with-a-few-samples&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-BBC2019-87"><span class="mw-cite-backlink"><b><a href="#cite_ref-BBC2019_87-0">^</a></b></span> <span class="reference-text"> <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.bbc.com/news/technology-48908736">"Fake voices 'help cyber-crooks steal cash'<span class="cs1-kern-right"></span>"</a>. <i><a href="/wiki/Bbc.com" class="mw-redirect" title="Bbc.com">bbc.com</a></i>. <a href="/wiki/BBC" title="BBC">BBC</a>. 2019-07-08<span class="reference-accessdate">. Retrieved <span class="nowrap">2019-09-11</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=bbc.com&rft.atitle=Fake+voices+%27help+cyber-crooks+steal+cash%27&rft.date=2019-07-08&rft_id=https%3A%2F%2Fwww.bbc.com%2Fnews%2Ftechnology-48908736&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-WaPo2019-88"><span class="mw-cite-backlink"><b><a href="#cite_ref-WaPo2019_88-0">^</a></b></span> <span class="reference-text"> <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFDrew2019" class="citation news cs1">Drew, Harwell (2019-09-04). <a rel="nofollow" class="external text" href="https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/">"An artificial-intelligence first: Voice-mimicking software reportedly used in a major theft"</a>. <i>Washington Post</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2019-09-08</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Washington+Post&rft.atitle=An+artificial-intelligence+first%3A+Voice-mimicking+software+reportedly+used+in+a+major+theft&rft.date=2019-09-04&rft.aulast=Drew&rft.aufirst=Harwell&rft_id=https%3A%2F%2Fwww.washingtonpost.com%2Ftechnology%2F2019%2F09%2F04%2Fan-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-Thi2016-89"><span class="mw-cite-backlink"><b><a href="#cite_ref-Thi2016_89-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFThies2016" class="citation web cs1">Thies, Justus (2016). <a rel="nofollow" class="external text" href="http://www.graphics.stanford.edu/~niessner/thies2016face.html">"Face2Face: Real-time Face Capture and Reenactment of RGB Videos"</a>. Proc. Computer Vision and Pattern Recognition (CVPR), IEEE<span class="reference-accessdate">. Retrieved <span class="nowrap">2016-06-18</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=Face2Face%3A+Real-time+Face+Capture+and+Reenactment+of+RGB+Videos&rft.pub=Proc.+Computer+Vision+and+Pattern+Recognition+%28CVPR%29%2C+IEEE&rft.date=2016&rft.aulast=Thies&rft.aufirst=Justus&rft_id=http%3A%2F%2Fwww.graphics.stanford.edu%2F~niessner%2Fthies2016face.html&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-Suw2017-90"><span class="mw-cite-backlink"><b><a href="#cite_ref-Suw2017_90-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFSuwajanakornSeitzKemelmacher-Shlizerman2017" class="citation cs2">Suwajanakorn, Supasorn; Seitz, Steven; Kemelmacher-Shlizerman, Ira (2017), <a rel="nofollow" class="external text" href="http://grail.cs.washington.edu/projects/AudioToObama/"><i>Synthesizing Obama: Learning Lip Sync from Audio</i></a>, <a href="/wiki/University_of_Washington" title="University of Washington">University of Washington</a><span class="reference-accessdate">, retrieved <span class="nowrap">2018-03-02</span></span></cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=book&rft.btitle=Synthesizing+Obama%3A+Learning+Lip+Sync+from+Audio&rft.pub=University+of+Washington&rft.date=2017&rft.aulast=Suwajanakorn&rft.aufirst=Supasorn&rft.au=Seitz%2C+Steven&rft.au=Kemelmacher-Shlizerman%2C+Ira&rft_id=http%3A%2F%2Fgrail.cs.washington.edu%2Fprojects%2FAudioToObama%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-Batch042020-91"><span class="mw-cite-backlink"><b><a href="#cite_ref-Batch042020_91-0">^</a></b></span> <span class="reference-text"> <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFNg2020" class="citation web cs1">Ng, Andrew (2020-04-01). <a rel="nofollow" class="external text" href="https://web.archive.org/web/20200807111844/https://blog.deeplearning.ai/blog/the-batch-ai-against-coronavirus-datasets-voice-cloning-for-the-masses-finding-unexploded-bombs-seeing-see-through-objects-optimizing-training-parameters">"Voice Cloning for the Masses"</a>. <i>deeplearning.ai</i>. The Batch. Archived from <a rel="nofollow" class="external text" href="https://blog.deeplearning.ai/blog/the-batch-ai-against-coronavirus-datasets-voice-cloning-for-the-masses-finding-unexploded-bombs-seeing-see-through-objects-optimizing-training-parameters">the original</a> on 2020-08-07<span class="reference-accessdate">. Retrieved <span class="nowrap">2020-04-02</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=deeplearning.ai&rft.atitle=Voice+Cloning+for+the+Masses&rft.date=2020-04-01&rft.aulast=Ng&rft.aufirst=Andrew&rft_id=https%3A%2F%2Fblog.deeplearning.ai%2Fblog%2Fthe-batch-ai-against-coronavirus-datasets-voice-cloning-for-the-masses-finding-unexploded-bombs-seeing-see-through-objects-optimizing-training-parameters&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-92"><span class="mw-cite-backlink"><b><a href="#cite_ref-92">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFBrunowCullen2021" class="citation journal cs1">Brunow, David A.; Cullen, Theresa A. (2021-07-03). <a rel="nofollow" class="external text" href="https://www.tandfonline.com/doi/full/10.1080/07380569.2021.1953362">"Effect of Text-to-Speech and Human Reader on Listening Comprehension for Students with Learning Disabilities"</a>. <i>Computers in the Schools</i>. <b>38</b> (3): 214–231. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1080%2F07380569.2021.1953362">10.1080/07380569.2021.1953362</a>. <a href="/wiki/Hdl_(identifier)" class="mw-redirect" title="Hdl (identifier)">hdl</a>:<span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://hdl.handle.net/11244%2F316759">11244/316759</a></span>. <a href="/wiki/ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/0738-0569">0738-0569</a>. <a href="/wiki/S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:243101945">243101945</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Computers+in+the+Schools&rft.atitle=Effect+of+Text-to-Speech+and+Human+Reader+on+Listening+Comprehension+for+Students+with+Learning+Disabilities&rft.volume=38&rft.issue=3&rft.pages=214-231&rft.date=2021-07-03&rft_id=info%3Ahdl%2F11244%2F316759&rft_id=https%3A%2F%2Fapi.semanticscholar.org%2FCorpusID%3A243101945%23id-name%3DS2CID&rft.issn=0738-0569&rft_id=info%3Adoi%2F10.1080%2F07380569.2021.1953362&rft.aulast=Brunow&rft.aufirst=David+A.&rft.au=Cullen%2C+Theresa+A.&rft_id=https%3A%2F%2Fwww.tandfonline.com%2Fdoi%2Ffull%2F10.1080%2F07380569.2021.1953362&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-93"><span class="mw-cite-backlink"><b><a href="#cite_ref-93">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFTriandafilidiTatarnikovaPoponin2022" class="citation book cs1">Triandafilidi, Ioanis I.; Tatarnikova, T. M.; Poponin, A. S. (2022-05-30). <a rel="nofollow" class="external text" href="https://ieeexplore.ieee.org/document/9803600">"Speech Synthesis System for People with Disabilities"</a>. <i>2022 Wave Electronics and its Application in Information and Telecommunication Systems (WECONF)</i>. St. Petersburg, Russian Federation: IEEE. pp. 1–5. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1109%2FWECONF55058.2022.9803600">10.1109/WECONF55058.2022.9803600</a>. <a href="/wiki/ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <a href="/wiki/Special:BookSources/978-1-6654-7083-4" title="Special:BookSources/978-1-6654-7083-4"><bdi>978-1-6654-7083-4</bdi></a>. <a href="/wiki/S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:250118756">250118756</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=bookitem&rft.atitle=Speech+Synthesis+System+for+People+with+Disabilities&rft.btitle=2022+Wave+Electronics+and+its+Application+in+Information+and+Telecommunication+Systems+%28WECONF%29&rft.place=St.+Petersburg%2C+Russian+Federation&rft.pages=1-5&rft.pub=IEEE&rft.date=2022-05-30&rft_id=https%3A%2F%2Fapi.semanticscholar.org%2FCorpusID%3A250118756%23id-name%3DS2CID&rft_id=info%3Adoi%2F10.1109%2FWECONF55058.2022.9803600&rft.isbn=978-1-6654-7083-4&rft.aulast=Triandafilidi&rft.aufirst=Ioanis+I.&rft.au=Tatarnikova%2C+T.+M.&rft.au=Poponin%2C+A.+S.&rft_id=https%3A%2F%2Fieeexplore.ieee.org%2Fdocument%2F9803600&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-94"><span class="mw-cite-backlink"><b><a href="#cite_ref-94">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFZhaoSongYueKuruvilla-Dugdale2021" class="citation book cs1">Zhao, Yunxin; Song, Minguang; Yue, Yanghao; Kuruvilla-Dugdale, Mili (2021-07-27). <a rel="nofollow" class="external text" href="https://ieeexplore.ieee.org/document/9508522">"Personalizing TTS Voices for Progressive Dysarthria"</a>. <i>2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI)</i>. Athens, Greece: IEEE. pp. 1–4. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1109%2FBHI50953.2021.9508522">10.1109/BHI50953.2021.9508522</a>. <a href="/wiki/ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <a href="/wiki/Special:BookSources/978-1-6654-0358-0" title="Special:BookSources/978-1-6654-0358-0"><bdi>978-1-6654-0358-0</bdi></a>. <a href="/wiki/S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:236982893">236982893</a>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=bookitem&rft.atitle=Personalizing+TTS+Voices+for+Progressive+Dysarthria&rft.btitle=2021+IEEE+EMBS+International+Conference+on+Biomedical+and+Health+Informatics+%28BHI%29&rft.place=Athens%2C+Greece&rft.pages=1-4&rft.pub=IEEE&rft.date=2021-07-27&rft_id=https%3A%2F%2Fapi.semanticscholar.org%2FCorpusID%3A236982893%23id-name%3DS2CID&rft_id=info%3Adoi%2F10.1109%2FBHI50953.2021.9508522&rft.isbn=978-1-6654-0358-0&rft.aulast=Zhao&rft.aufirst=Yunxin&rft.au=Song%2C+Minguang&rft.au=Yue%2C+Yanghao&rft.au=Kuruvilla-Dugdale%2C+Mili&rft_id=https%3A%2F%2Fieeexplore.ieee.org%2Fdocument%2F9508522&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-95"><span class="mw-cite-backlink"><b><a href="#cite_ref-95">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation journal cs1"><a rel="nofollow" class="external text" href="https://www.rehab.research.va.gov/jour/84/21/1/pdf/cooper.pdf">"Evolution of Reading Machines for the Blind: Haskins Laboratories" Research as a Case History"</a> <span class="cs1-format">(PDF)</span>. <i><a href="/wiki/Journal_of_Rehabilitation_Research_and_Development" title="Journal of Rehabilitation Research and Development">Journal of Rehabilitation Research and Development</a></i>. <b>21</b> (1). 1984.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Journal+of+Rehabilitation+Research+and+Development&rft.atitle=Evolution+of+Reading+Machines+for+the+Blind%3A+Haskins+Laboratories%22+Research+as+a+Case+History&rft.volume=21&rft.issue=1&rft.date=1984&rft_id=https%3A%2F%2Fwww.rehab.research.va.gov%2Fjour%2F84%2F21%2F1%2Fpdf%2Fcooper.pdf&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-96"><span class="mw-cite-backlink"><b><a href="#cite_ref-96">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation news cs1"><a rel="nofollow" class="external text" href="http://www.animenewsnetwork.com/news/2007-05-02/speech-synthesis-software">"Speech Synthesis Software for Anime Announced"</a>. <i>Anime News Network</i>. 2007-05-02<span class="reference-accessdate">. Retrieved <span class="nowrap">2010-02-17</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Anime+News+Network&rft.atitle=Speech+Synthesis+Software+for+Anime+Announced&rft.date=2007-05-02&rft_id=http%3A%2F%2Fwww.animenewsnetwork.com%2Fnews%2F2007-05-02%2Fspeech-synthesis-software&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-97"><span class="mw-cite-backlink"><b><a href="#cite_ref-97">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://www.animenewsnetwork.com/news/2008-09-09/code-geass-voice-synthesis-service-offered-in-japan">"Code Geass Speech Synthesizer Service Offered in Japan"</a>. Animenewsnetwork.com. 2008-09-09<span class="reference-accessdate">. Retrieved <span class="nowrap">2010-02-17</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=unknown&rft.btitle=Code+Geass+Speech+Synthesizer+Service+Offered+in+Japan&rft.pub=Animenewsnetwork.com&rft.date=2008-09-09&rft_id=http%3A%2F%2Fwww.animenewsnetwork.com%2Fnews%2F2008-09-09%2Fcode-geass-voice-synthesis-service-offered-in-japan&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-:162-98"><span class="mw-cite-backlink"><b><a href="#cite_ref-:162_98-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://venturebeat.com/ai/now-hear-this-voice-cloning-ai-startup-elevenlabs-nabs-19m-from-a16z-and-other-heavy-hitters/">"Now hear this: Voice cloning AI startup ElevenLabs nabs $19M from a16z and other heavy hitters"</a>. <i>VentureBeat</i>. 2023-06-20<span class="reference-accessdate">. Retrieved <span class="nowrap">2023-07-25</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=VentureBeat&rft.atitle=Now+hear+this%3A+Voice+cloning+AI+startup+ElevenLabs+nabs+%2419M+from+a16z+and+other+heavy+hitters&rft.date=2023-06-20&rft_id=https%3A%2F%2Fventurebeat.com%2Fai%2Fnow-hear-this-voice-cloning-ai-startup-elevenlabs-nabs-19m-from-a16z-and-other-heavy-hitters%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-99"><span class="mw-cite-backlink"><b><a href="#cite_ref-99">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1 cs1-prop-foreign-lang-source"><a rel="nofollow" class="external text" href="https://www.press.pl/tresc/75988,sztuczna-inteligencja-czyta-glosem-jaroslawa-kuzniara_-to-zapowiedz-rewolucji-w-radiu-i-podcastach">"Sztuczna inteligencja czyta głosem Jarosława Kuźniara. Rewolucja w radiu i podcastach"</a>. <i>Press.pl</i> (in Polish). April 9, 2023<span class="reference-accessdate">. Retrieved <span class="nowrap">2023-04-25</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=Press.pl&rft.atitle=Sztuczna+inteligencja+czyta+g%C5%82osem+Jaros%C5%82awa+Ku%C5%BAniara.+Rewolucja+w+radiu+i+podcastach&rft.date=2023-04-09&rft_id=https%3A%2F%2Fwww.press.pl%2Ftresc%2F75988%2Csztuczna-inteligencja-czyta-glosem-jaroslawa-kuzniara_-to-zapowiedz-rewolucji-w-radiu-i-podcastach&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-100"><span class="mw-cite-backlink"><b><a href="#cite_ref-100">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFKnibbs" class="citation magazine cs1">Knibbs, Kate. <a rel="nofollow" class="external text" href="https://www.wired.com/story/generative-ai-podcasts-boring/">"Generative AI Podcasts Are Here. Prepare to Be Bored"</a>. <i>Wired</i>. <a href="/wiki/ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/1059-1028">1059-1028</a><span class="reference-accessdate">. Retrieved <span class="nowrap">2023-07-25</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=Wired&rft.atitle=Generative+AI+Podcasts+Are+Here.+Prepare+to+Be+Bored&rft.issn=1059-1028&rft.aulast=Knibbs&rft.aufirst=Kate&rft_id=https%3A%2F%2Fwww.wired.com%2Fstory%2Fgenerative-ai-podcasts-boring%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-101"><span class="mw-cite-backlink"><b><a href="#cite_ref-101">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFSuciu" class="citation web cs1">Suciu, Peter. <a rel="nofollow" class="external text" href="https://www.forbes.com/sites/petersuciu/2023/05/09/arrested-succession-parody-on-youtube-features-narration-by-ai-generated-ron-howard/">"Arrested Succession Parody On YouTube Features 'Narration' By AI-Generated Ron Howard"</a>. <i>Forbes</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2023-07-25</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=Forbes&rft.atitle=Arrested+Succession+Parody+On+YouTube+Features+%27Narration%27+By+AI-Generated+Ron+Howard&rft.aulast=Suciu&rft.aufirst=Peter&rft_id=https%3A%2F%2Fwww.forbes.com%2Fsites%2Fpetersuciu%2F2023%2F05%2F09%2Farrested-succession-parody-on-youtube-features-narration-by-ai-generated-ron-howard%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-102"><span class="mw-cite-backlink"><b><a href="#cite_ref-102">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFFadulu2023" class="citation news cs1">Fadulu, Lola (2023-07-06). <a rel="nofollow" class="external text" href="https://www.nytimes.com/2023/07/06/nyregion/artificial-intelligence-comedy.html">"Can A.I. Be Funny? This Troupe Thinks So"</a>. <i>The New York Times</i>. <a href="/wiki/ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/0362-4331">0362-4331</a><span class="reference-accessdate">. Retrieved <span class="nowrap">2023-07-25</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.jtitle=The+New+York+Times&rft.atitle=Can+A.I.+Be+Funny%3F+This+Troupe+Thinks+So.&rft.date=2023-07-06&rft.issn=0362-4331&rft.aulast=Fadulu&rft.aufirst=Lola&rft_id=https%3A%2F%2Fwww.nytimes.com%2F2023%2F07%2F06%2Fnyregion%2Fartificial-intelligence-comedy.html&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-:2-103"><span class="mw-cite-backlink"><b><a href="#cite_ref-:2_103-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFKanetkar" class="citation web cs1">Kanetkar, Riddhi. <a rel="nofollow" class="external text" href="https://www.businessinsider.com/elevenlabs-ai-voice-intelligence-startup-raises-2-million-2023-1">"Hot AI startup ElevenLabs, founded by ex-Google and Palantir staff, is set to raise $18 million at a $100 million valuation. Check out the 14-slide pitch deck it used for its $2 million pre-seed"</a>. <i>Business Insider</i><span class="reference-accessdate">. Retrieved <span class="nowrap">2023-07-25</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=Business+Insider&rft.atitle=Hot+AI+startup+ElevenLabs%2C+founded+by+ex-Google+and+Palantir+staff%2C+is+set+to+raise+%2418+million+at+a+%24100+million+valuation.+Check+out+the+14-slide+pitch+deck+it+used+for+its+%242+million+pre-seed.&rft.aulast=Kanetkar&rft.aufirst=Riddhi&rft_id=https%3A%2F%2Fwww.businessinsider.com%2Felevenlabs-ai-voice-intelligence-startup-raises-2-million-2023-1&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-:02-104"><span class="mw-cite-backlink"><b><a href="#cite_ref-:02_104-0">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.vice.com/en/article/dy7mww/ai-voice-firm-4chan-celebrity-voices-emma-watson-joe-rogan-elevenlabs">"AI-Generated Voice Firm Clamps Down After 4chan Makes Celebrity Voices for Abuse"</a>. <i>www.vice.com</i>. January 30, 2023<span class="reference-accessdate">. Retrieved <span class="nowrap">2023-02-03</span></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=www.vice.com&rft.atitle=AI-Generated+Voice+Firm+Clamps+Down+After+4chan+Makes+Celebrity+Voices+for+Abuse&rft.date=2023-01-30&rft_id=https%3A%2F%2Fwww.vice.com%2Fen%2Farticle%2Fdy7mww%2Fai-voice-firm-4chan-celebrity-voices-emma-watson-joe-rogan-elevenlabs&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-105"><span class="mw-cite-backlink"><b><a href="#cite_ref-105">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://elai.io/">"Usage of text-to-speech in AI video generation"</a>. <i>elai.io</i><span class="reference-accessdate">. Retrieved <span class="nowrap">10 August</span> 2022</span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=elai.io&rft.atitle=Usage+of+text-to-speech+in+AI+video+generation&rft_id=https%3A%2F%2Felai.io%2F&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-106"><span class="mw-cite-backlink"><b><a href="#cite_ref-106">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.synthesia.io/text-to-speech">"AI Text to speech for videos"</a>. <i>synthesia.io</i><span class="reference-accessdate">. Retrieved <span class="nowrap">12 October</span> 2023</span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=unknown&rft.jtitle=synthesia.io&rft.atitle=AI+Text+to+speech+for+videos&rft_id=https%3A%2F%2Fwww.synthesia.io%2Ftext-to-speech&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> <li id="cite_note-107"><span class="mw-cite-backlink"><b><a href="#cite_ref-107">^</a></b></span> <span class="reference-text"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1238218222"><cite id="CITEREFBruno2014" class="citation thesis cs1">Bruno, Chelsea A (2014-03-25). <a rel="nofollow" class="external text" href="http://digitalcommons.fiu.edu/etd/1245"><i>Vocal Synthesis and Deep Listening</i></a> (Master of Music Music thesis). Florida International University. <a href="/wiki/Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<span class="id-lock-free" title="Freely accessible"><a rel="nofollow" class="external text" href="https://doi.org/10.25148%2Fetd.fi14040802">10.25148/etd.fi14040802</a></span>.</cite><span title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adissertation&rft.title=Vocal+Synthesis+and+Deep+Listening&rft.degree=Master+of+Music+Music&rft.inst=Florida+International+University&rft.date=2014-03-25&rft_id=info%3Adoi%2F10.25148%2Fetd.fi14040802&rft.aulast=Bruno&rft.aufirst=Chelsea+A&rft_id=http%3A%2F%2Fdigitalcommons.fiu.edu%2Fetd%2F1245&rfr_id=info%3Asid%2Fen.wikipedia.org%3ASpeech+synthesis" class="Z3988"></span></span> </li> </ol></div></div> <div class="mw-heading mw-heading2"><h2 id="External_links">External links</h2><span class="mw-editsection"><span class="mw-editsection-bracket">[</span><a href="/w/index.php?title=Speech_synthesis&action=edit&section=41" title="Edit section: External links"><span>edit</span></a><span class="mw-editsection-bracket">]</span></span></div> <link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1235681985"><style data-mw-deduplicate="TemplateStyles:r1237033735">@media print{body.ns-0 .mw-parser-output .sistersitebox{display:none!important}}@media screen{html.skin-theme-clientpref-night .mw-parser-output .sistersitebox img[src*="Wiktionary-logo-en-v2.svg"]{background-color:white}}@media screen and (prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .sistersitebox img[src*="Wiktionary-logo-en-v2.svg"]{background-color:white}}</style><div class="side-box side-box-right plainlinks sistersitebox"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1126788409"> <div class="side-box-flex"> <div class="side-box-image"><span class="noviewer" typeof="mw:File"><span><img alt="" src="//upload.wikimedia.org/wikipedia/en/thumb/4/4a/Commons-logo.svg/30px-Commons-logo.svg.png" decoding="async" width="30" height="40" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/en/thumb/4/4a/Commons-logo.svg/45px-Commons-logo.svg.png 1.5x, //upload.wikimedia.org/wikipedia/en/thumb/4/4a/Commons-logo.svg/59px-Commons-logo.svg.png 2x" data-file-width="1024" data-file-height="1376" /></span></span></div> <div class="side-box-text plainlist">Wikimedia Commons has media related to <span style="font-weight: bold; font-style: italic;"><a href="https://commons.wikimedia.org/wiki/Category:Speech_synthesis" class="extiw" title="commons:Category:Speech synthesis">Speech synthesis</a></span>.</div></div> </div> <ul><li><a rel="nofollow" class="external text" href="https://www.youtube.com/watch?v=CE6zy8aUwtQ">Simulated singing with the singing robot Pavarobotti</a> or a description from the <a href="/wiki/BBC" title="BBC">BBC</a> on <a rel="nofollow" class="external text" href="https://www.youtube.com/watch?v=SNqNM6Ccck8">how the robot synthesized the singing</a>.</li></ul> <div class="navbox-styles"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1129693374"><style data-mw-deduplicate="TemplateStyles:r1236075235">.mw-parser-output .navbox{box-sizing:border-box;border:1px solid #a2a9b1;width:100%;clear:both;font-size:88%;text-align:center;padding:1px;margin:1em auto 0}.mw-parser-output .navbox .navbox{margin-top:0}.mw-parser-output .navbox+.navbox,.mw-parser-output .navbox+.navbox-styles+.navbox{margin-top:-1px}.mw-parser-output .navbox-inner,.mw-parser-output .navbox-subgroup{width:100%}.mw-parser-output .navbox-group,.mw-parser-output .navbox-title,.mw-parser-output .navbox-abovebelow{padding:0.25em 1em;line-height:1.5em;text-align:center}.mw-parser-output .navbox-group{white-space:nowrap;text-align:right}.mw-parser-output .navbox,.mw-parser-output .navbox-subgroup{background-color:#fdfdfd}.mw-parser-output .navbox-list{line-height:1.5em;border-color:#fdfdfd}.mw-parser-output .navbox-list-with-group{text-align:left;border-left-width:2px;border-left-style:solid}.mw-parser-output tr+tr>.navbox-abovebelow,.mw-parser-output tr+tr>.navbox-group,.mw-parser-output tr+tr>.navbox-image,.mw-parser-output tr+tr>.navbox-list{border-top:2px solid #fdfdfd}.mw-parser-output .navbox-title{background-color:#ccf}.mw-parser-output .navbox-abovebelow,.mw-parser-output .navbox-group,.mw-parser-output .navbox-subgroup .navbox-title{background-color:#ddf}.mw-parser-output .navbox-subgroup .navbox-group,.mw-parser-output .navbox-subgroup .navbox-abovebelow{background-color:#e6e6ff}.mw-parser-output .navbox-even{background-color:#f7f7f7}.mw-parser-output .navbox-odd{background-color:transparent}.mw-parser-output .navbox .hlist td dl,.mw-parser-output .navbox .hlist td ol,.mw-parser-output .navbox .hlist td ul,.mw-parser-output .navbox td.hlist dl,.mw-parser-output .navbox td.hlist ol,.mw-parser-output .navbox td.hlist ul{padding:0.125em 0}.mw-parser-output .navbox .navbar{display:block;font-size:100%}.mw-parser-output .navbox-title .navbar{float:left;text-align:left;margin-right:0.5em}body.skin--responsive .mw-parser-output .navbox-image img{max-width:none!important}@media print{body.ns-0 .mw-parser-output .navbox{display:none!important}}</style></div><div role="navigation" class="navbox" aria-labelledby="Sound_synthesis_types" style="padding:3px"><table class="nowraplinks hlist mw-collapsible autocollapse navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1129693374"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1239400231"><div class="navbar plainlinks hlist navbar-mini"><ul><li class="nv-view"><a href="/wiki/Template:Sound_synthesis_types" title="Template:Sound synthesis types"><abbr title="View this template">v</abbr></a></li><li class="nv-talk"><a href="/wiki/Template_talk:Sound_synthesis_types" title="Template talk:Sound synthesis types"><abbr title="Discuss this template">t</abbr></a></li><li class="nv-edit"><a href="/wiki/Special:EditPage/Template:Sound_synthesis_types" title="Special:EditPage/Template:Sound synthesis types"><abbr title="Edit this template">e</abbr></a></li></ul></div><div id="Sound_synthesis_types" style="font-size:114%;margin:0 4em"><a href="/wiki/Synthesizer" title="Synthesizer">Sound synthesis</a> types</div></th></tr><tr><td class="navbox-abovebelow" colspan="2"><div> <ul><li><a href="/wiki/Frequency_modulation_synthesis" title="Frequency modulation synthesis">Frequency modulation</a></li> <li><a href="/wiki/Linear_arithmetic_synthesis" title="Linear arithmetic synthesis">Linear arithmetic</a></li> <li><a href="/wiki/Phase_distortion_synthesis" title="Phase distortion synthesis">Phase distortion</a></li> <li><a href="/wiki/Scanned_synthesis" title="Scanned synthesis">Scanned</a></li> <li><a href="/wiki/Subtractive_synthesis" title="Subtractive synthesis">Subtractive</a></li> <li><a href="/wiki/Additive_synthesis" title="Additive synthesis">Additive</a></li> <li><a href="/wiki/Distortion_synthesis" title="Distortion synthesis">Distortion</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Sample-based_synthesis" title="Sample-based synthesis">Sample-based</a> or <a href="/wiki/Sampler_(musical_instrument)" title="Sampler (musical instrument)">Sampler</a></th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Wavetable_synthesis" title="Wavetable synthesis">Wavetable</a></li> <li><a href="/wiki/Granular_synthesis" title="Granular synthesis">Granular</a></li> <li><a href="/wiki/Vector_synthesis" title="Vector synthesis">Vector</a></li> <li><a href="/wiki/Concatenative_synthesis" title="Concatenative synthesis">Concatenative</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Physical_modelling_synthesis" title="Physical modelling synthesis">Physical modelling</a></th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Banded_waveguide_synthesis" title="Banded waveguide synthesis">Banded waveguide</a></li> <li><a href="/wiki/Digital_waveguide_synthesis" title="Digital waveguide synthesis">Digital waveguide</a></li> <li><a href="/wiki/Direct_digital_synthesizer" class="mw-redirect" title="Direct digital synthesizer">Direct digital</a></li> <li><a href="/wiki/Formant_synthesis" class="mw-redirect" title="Formant synthesis">Formant</a></li> <li><a href="/wiki/Karplus%E2%80%93Strong_string_synthesis" title="Karplus–Strong string synthesis">Karplus–Strong string</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Analog_synthesizer" title="Analog synthesizer">Analog synthesizer</a></th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Graphical_sound" title="Graphical sound">Graphical sound</a></li> <li><a href="/wiki/Modular_synthesizer" title="Modular synthesizer">Modular</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Digital_synthesizer" title="Digital synthesizer">Digital synthesizer</a></th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Analog_modeling_synthesizer" title="Analog modeling synthesizer">Analog modeling</a></li> <li><a href="/wiki/Scanned_synthesis" title="Scanned synthesis">Scanned synthesis</a></li> <li><a href="/wiki/Software_synthesizer" title="Software synthesizer">Software synthesizer</a></li></ul> </div></td></tr></tbody></table></div> <div class="navbox-styles"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1129693374"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1236075235"></div><div role="navigation" class="navbox" aria-labelledby="Speech_synthesis" style="padding:3px"><table class="nowraplinks mw-collapsible autocollapse navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2" style="background: Silver;"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1129693374"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1239400231"><div class="navbar plainlinks hlist navbar-mini"><ul><li class="nv-view"><a href="/wiki/Template:Speech_synthesis" title="Template:Speech synthesis"><abbr title="View this template">v</abbr></a></li><li class="nv-talk"><a href="/wiki/Template_talk:Speech_synthesis" title="Template talk:Speech synthesis"><abbr title="Discuss this template">t</abbr></a></li><li class="nv-edit"><a href="/wiki/Special:EditPage/Template:Speech_synthesis" title="Special:EditPage/Template:Speech synthesis"><abbr title="Edit this template">e</abbr></a></li></ul></div><div id="Speech_synthesis" style="font-size:114%;margin:0 4em"><a class="mw-selflink selflink">Speech synthesis</a></div></th></tr><tr><th scope="row" class="navbox-group" style="width:1%;background: Gainsboro;"><a href="/wiki/Free_software" title="Free software">Free software</a></th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em"></div><table class="nowraplinks navbox-subgroup" style="border-spacing:0"><tbody><tr><th scope="row" class="navbox-group" style="width:1%">Speaking</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/ESpeak" title="ESpeak">eSpeak</a>/<a href="/wiki/ESpeakNG" class="mw-redirect" title="ESpeakNG">eSpeakNG</a></li> <li><a href="/wiki/Gnopernicus" title="Gnopernicus">Gnopernicus</a></li> <li><a href="/wiki/Gnuspeech" title="Gnuspeech">Gnuspeech</a></li> <li><a href="/wiki/Orca_(assistive_technology)" title="Orca (assistive technology)">Orca</a></li> <li><a href="/wiki/Festival_Speech_Synthesis_System" title="Festival Speech Synthesis System">Festival Speech Synthesis System</a>/<a href="/wiki/Festival_Speech_Synthesis_System#Flite" title="Festival Speech Synthesis System">Flite</a></li> <li><a href="/wiki/FreeTTS" title="FreeTTS">FreeTTS</a></li> <li><a href="/wiki/Automatik_Text_Reader" title="Automatik Text Reader">Automatik Text Reader</a></li> <li><a href="/wiki/Retrieval-based_Voice_Conversion" title="Retrieval-based Voice Conversion">Retrieval-based Voice Conversion</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Singing</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/ESpeak" title="ESpeak">eCantorix</a></li> <li><a href="/wiki/Festival_Speech_Synthesis_System" title="Festival Speech Synthesis System">Lyricos / Flinger</a></li> <li><a href="/wiki/Sinsy" title="Sinsy">Sinsy</a></li> <li><a href="/wiki/Retrieval-based_Voice_Conversion" title="Retrieval-based Voice Conversion">Retrieval-based Voice Conversion</a></li></ul> </div></td></tr></tbody></table><div></div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%;background: Gainsboro;"><a href="/wiki/Proprietary_software" title="Proprietary software">Proprietary <br />software</a></th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em"></div><table class="nowraplinks navbox-subgroup" style="border-spacing:0"><tbody><tr><th scope="row" class="navbox-group" style="width:1%">Speaking</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Amazon_Polly" title="Amazon Polly">Amazon Polly</a></li> <li><a href="/wiki/DECtalk" title="DECtalk">DECtalk</a></li> <li><a href="/wiki/Software_Automatic_Mouth" title="Software Automatic Mouth">Software Automatic Mouth</a></li> <li><a href="/wiki/Talk_It!" class="mw-redirect" title="Talk It!">Talk It!</a></li> <li><a href="/wiki/Microsoft_Agent" title="Microsoft Agent">Microsoft Agent</a></li> <li><a href="/wiki/Microsoft_Speech_API" title="Microsoft Speech API">Microsoft Speech API</a></li> <li><a href="/wiki/Microsoft_text-to-speech_voices" title="Microsoft text-to-speech voices">Microsoft text-to-speech voices</a></li> <li><a href="/wiki/Readspeaker" class="mw-redirect" title="Readspeaker">Readspeaker</a></li> <li><a href="/wiki/Voice_browser" title="Voice browser">Voice browser</a></li> <li><a href="/wiki/CoolSpeech" title="CoolSpeech">CoolSpeech</a></li> <li><a href="/wiki/IVONA" class="mw-redirect" title="IVONA">IVONA</a></li> <li><a href="/wiki/CereProc" title="CereProc">CereProc</a></li> <li><a href="/wiki/CeVIO_Creative_Studio" class="mw-redirect" title="CeVIO Creative Studio">CeVIO Creative Studio</a></li> <li><a href="/wiki/Voiceroid" title="Voiceroid">Voiceroid</a></li> <li><a href="/wiki/LaLaVoice" title="LaLaVoice">LaLaVoice</a></li> <li><a href="/wiki/15.ai" title="15.ai">15.ai</a></li> <li><a href="/wiki/ElevenLabs" title="ElevenLabs">ElevenLabs</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Singing</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Alter/Ego" title="Alter/Ego">Alter/Ego</a></li> <li><a href="/wiki/Cantor_(music_software)" title="Cantor (music software)">Cantor</a></li> <li><a href="/wiki/CeVIO" title="CeVIO">CeVIO Creative Studio</a></li> <li><a href="/wiki/Chipspeech" title="Chipspeech">Chipspeech</a></li> <li><a href="/wiki/NIAONiao_Virtual_Singer" title="NIAONiao Virtual Singer">NIAONiao Virtual Singer</a></li> <li><a href="/wiki/PPG_Phonem" title="PPG Phonem">PPG Phonem</a></li> <li><a href="/w/index.php?title=Realivox&action=edit&redlink=1" class="new" title="Realivox (page does not exist)">Realivox</a></li> <li><a href="/wiki/Symphonic_Choirs" title="Symphonic Choirs">Symphonic Choirs</a></li> <li><a href="/wiki/Utau" title="Utau">UTAU</a></li> <li><a href="/wiki/Vocalina" title="Vocalina">Vocalina</a></li> <li><a href="/wiki/Vocaloid" title="Vocaloid">Vocaloid</a></li> <li><a href="/wiki/Xiaoice#Singer" title="Xiaoice">Xiaoice</a></li></ul> </div></td></tr></tbody></table><div></div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%;background: Gainsboro;">Machine</th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Echo_II_(expansion_card)" title="Echo II (expansion card)">Echo II</a></li> <li><a href="/wiki/Mockingboard" title="Mockingboard">Mockingboard</a></li> <li><a href="/wiki/Pattern_playback" title="Pattern playback">Pattern playback</a></li> <li><a href="/wiki/Phasor_(sound_synthesizer)" title="Phasor (sound synthesizer)">Phasor</a></li> <li><a href="/wiki/Remote_infrared_audible_signage" title="Remote infrared audible signage">RIAS</a></li> <li><a href="/wiki/Texas_Instruments_LPC_Speech_Chips" title="Texas Instruments LPC Speech Chips">Texas Instruments LPC Speech Chips</a></li> <li><a href="/wiki/General_Instrument_SP0256" title="General Instrument SP0256">General Instrument SP0256</a></li> <li><a href="/wiki/TuVox" title="TuVox">TuVox</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%;background: Gainsboro;">Applications</th><td class="navbox-list-with-group navbox-list navbox-even hlist" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/AOLbyPhone" class="mw-redirect" title="AOLbyPhone">AOLbyPhone</a></li> <li><a href="/wiki/DialogOS" title="DialogOS">DialogOS</a></li> <li><a href="/wiki/Dr._Sbaitso" title="Dr. Sbaitso">Dr. Sbaitso</a></li> <li><a href="/wiki/MBROLA" title="MBROLA">MBROLA</a></li> <li><a href="/wiki/Narrator_(Windows)" title="Narrator (Windows)">Windows Narrator</a></li> <li><a href="/wiki/Microsoft_Speech_Server" title="Microsoft Speech Server">Microsoft Speech Server</a></li> <li><a href="/wiki/PlainTalk" title="PlainTalk">PlainTalk</a></li> <li><a href="/wiki/Voice_font" title="Voice font">Voice font</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%;background: Gainsboro;">Protocols</th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Speech_Synthesis_Markup_Language" title="Speech Synthesis Markup Language">Speech Synthesis Markup Language</a></li> <li><a href="/wiki/SABLE" title="SABLE">SABLE</a></li> <li><a href="/wiki/VoiceXML" title="VoiceXML">VoiceXML</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%;background: Gainsboro;">Developers/<br />Researchers</th><td class="navbox-list-with-group navbox-list navbox-even hlist" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Alan_W._Black" title="Alan W. Black">Alan W. Black</a></li> <li><a href="/wiki/Catherine_Browman" title="Catherine Browman">Catherine Browman</a></li> <li><a href="/wiki/Franklin_Seaney_Cooper" class="mw-redirect" title="Franklin Seaney Cooper">Franklin Seaney Cooper</a></li> <li><a href="/wiki/Gunnar_Fant" title="Gunnar Fant">Gunnar Fant</a></li> <li><a href="/wiki/Haskins_Laboratories" title="Haskins Laboratories">Haskins Laboratories</a></li> <li><a href="/wiki/Wolfgang_von_Kempelen" title="Wolfgang von Kempelen">Wolfgang von Kempelen</a></li> <li><a href="/wiki/Ignatius_Mattingly" title="Ignatius Mattingly">Ignatius Mattingly</a></li> <li><a href="/wiki/Philip_Rubin" title="Philip Rubin">Philip Rubin</a></li> <li><a href="/wiki/Yamaha_Corporation" title="Yamaha Corporation">Yamaha</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%;background: Gainsboro;">Process</th><td class="navbox-list-with-group navbox-list navbox-odd hlist" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Articulatory_synthesis" title="Articulatory synthesis">Articulatory synthesis</a></li> <li><a href="/wiki/Concatenative_synthesis" title="Concatenative synthesis">Concatenative synthesis</a></li> <li><a href="/wiki/Currah" title="Currah">Currah</a></li> <li><a href="/wiki/Inverse_filter" title="Inverse filter">Inverse filter</a></li> <li><a href="/wiki/PSOLA" title="PSOLA">PSOLA</a></li> <li><a href="/wiki/Phase_vocoder" title="Phase vocoder">Phase vocoder</a></li> <li><a href="/wiki/Self-voicing" title="Self-voicing">Self-voicing</a></li> <li><a href="/wiki/Voice_cloning" class="mw-redirect" title="Voice cloning">Voice cloning</a></li></ul> </div></td></tr></tbody></table></div> <div class="navbox-styles"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1129693374"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1236075235"></div><div role="navigation" class="navbox" aria-labelledby="Natural_language_processing" style="padding:3px"><table class="nowraplinks hlist mw-collapsible autocollapse navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1129693374"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1239400231"><div class="navbar plainlinks hlist navbar-mini"><ul><li class="nv-view"><a href="/wiki/Template:Natural_language_processing" title="Template:Natural language processing"><abbr title="View this template">v</abbr></a></li><li class="nv-talk"><a href="/wiki/Template_talk:Natural_language_processing" title="Template talk:Natural language processing"><abbr title="Discuss this template">t</abbr></a></li><li class="nv-edit"><a href="/wiki/Special:EditPage/Template:Natural_language_processing" title="Special:EditPage/Template:Natural language processing"><abbr title="Edit this template">e</abbr></a></li></ul></div><div id="Natural_language_processing" style="font-size:114%;margin:0 4em"><a href="/wiki/Natural_language_processing" title="Natural language processing">Natural language processing</a></div></th></tr><tr><th scope="row" class="navbox-group" style="width:1%">General terms</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/AI-complete" title="AI-complete">AI-complete</a></li> <li><a href="/wiki/Bag-of-words_model" title="Bag-of-words model">Bag-of-words</a></li> <li><a href="/wiki/N-gram" title="N-gram">n-gram</a> <ul><li><a href="/wiki/Bigram" title="Bigram">Bigram</a></li> <li><a href="/wiki/Trigram" title="Trigram">Trigram</a></li></ul></li> <li><a href="/wiki/Computational_linguistics" title="Computational linguistics">Computational linguistics</a></li> <li><a href="/wiki/Natural_language_understanding" title="Natural language understanding">Natural language understanding</a></li> <li><a href="/wiki/Stop_word" title="Stop word">Stop words</a></li> <li><a href="/wiki/Text_processing" title="Text processing">Text processing</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Text_mining" title="Text mining">Text analysis</a></th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Argument_mining" title="Argument mining">Argument mining</a></li> <li><a href="/wiki/Collocation_extraction" title="Collocation extraction">Collocation extraction</a></li> <li><a href="/wiki/Concept_mining" title="Concept mining">Concept mining</a></li> <li><a href="/wiki/Coreference#Coreference_resolution" title="Coreference">Coreference resolution</a></li> <li><a href="/wiki/Deep_linguistic_processing" title="Deep linguistic processing">Deep linguistic processing</a></li> <li><a href="/wiki/Distant_reading" title="Distant reading">Distant reading</a></li> <li><a href="/wiki/Information_extraction" title="Information extraction">Information extraction</a></li> <li><a href="/wiki/Named-entity_recognition" title="Named-entity recognition">Named-entity recognition</a></li> <li><a href="/wiki/Ontology_learning" title="Ontology learning">Ontology learning</a></li> <li><a href="/wiki/Parsing" title="Parsing">Parsing</a> <ul><li><a href="/wiki/Semantic_parsing" title="Semantic parsing">Semantic parsing</a></li> <li><a href="/wiki/Syntactic_parsing_(computational_linguistics)" title="Syntactic parsing (computational linguistics)">Syntactic parsing</a></li></ul></li> <li><a href="/wiki/Part-of-speech_tagging" title="Part-of-speech tagging">Part-of-speech tagging</a></li> <li><a href="/wiki/Semantic_analysis_(machine_learning)" title="Semantic analysis (machine learning)">Semantic analysis</a></li> <li><a href="/wiki/Semantic_role_labeling" title="Semantic role labeling">Semantic role labeling</a></li> <li><a href="/wiki/Semantic_decomposition_(natural_language_processing)" title="Semantic decomposition (natural language processing)">Semantic decomposition</a></li> <li><a href="/wiki/Semantic_similarity" title="Semantic similarity">Semantic similarity</a></li> <li><a href="/wiki/Sentiment_analysis" title="Sentiment analysis">Sentiment analysis</a></li></ul> <ul><li><a href="/wiki/Terminology_extraction" title="Terminology extraction">Terminology extraction</a></li> <li><a href="/wiki/Text_mining" title="Text mining">Text mining</a></li> <li><a href="/wiki/Textual_entailment" title="Textual entailment">Textual entailment</a></li> <li><a href="/wiki/Truecasing" title="Truecasing">Truecasing</a></li> <li><a href="/wiki/Word-sense_disambiguation" title="Word-sense disambiguation">Word-sense disambiguation</a></li> <li><a href="/wiki/Word-sense_induction" title="Word-sense induction">Word-sense induction</a></li></ul> </div><table class="nowraplinks navbox-subgroup" style="border-spacing:0"><tbody><tr><th id="Text_segmentation" scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Text_segmentation" title="Text segmentation">Text segmentation</a></th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Compound-term_processing" title="Compound-term processing">Compound-term processing</a></li> <li><a href="/wiki/Lemmatisation" class="mw-redirect" title="Lemmatisation">Lemmatisation</a></li> <li><a href="/wiki/Lexical_analysis" title="Lexical analysis">Lexical analysis</a></li> <li><a href="/wiki/Shallow_parsing" title="Shallow parsing">Text chunking</a></li> <li><a href="/wiki/Stemming" title="Stemming">Stemming</a></li> <li><a href="/wiki/Sentence_boundary_disambiguation" title="Sentence boundary disambiguation">Sentence segmentation</a></li> <li><a href="/wiki/Word#Word_boundaries" title="Word">Word segmentation</a></li></ul> </div></td></tr></tbody></table><div> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Automatic_summarization" title="Automatic summarization">Automatic summarization</a></th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Multi-document_summarization" title="Multi-document summarization">Multi-document summarization</a></li> <li><a href="/wiki/Sentence_extraction" title="Sentence extraction">Sentence extraction</a></li> <li><a href="/wiki/Text_simplification" title="Text simplification">Text simplification</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Machine_translation" title="Machine translation">Machine translation</a></th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Computer-assisted_translation" title="Computer-assisted translation">Computer-assisted</a></li> <li><a href="/wiki/Example-based_machine_translation" title="Example-based machine translation">Example-based</a></li> <li><a href="/wiki/Rule-based_machine_translation" title="Rule-based machine translation">Rule-based</a></li> <li><a href="/wiki/Statistical_machine_translation" title="Statistical machine translation">Statistical</a></li> <li><a href="/wiki/Transfer-based_machine_translation" title="Transfer-based machine translation">Transfer-based</a></li> <li><a href="/wiki/Neural_machine_translation" title="Neural machine translation">Neural</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Distributional_semantics" title="Distributional semantics">Distributional semantics</a> models</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/BERT_(language_model)" title="BERT (language model)">BERT</a></li> <li><a href="/wiki/Document-term_matrix" title="Document-term matrix">Document-term matrix</a></li> <li><a href="/wiki/Explicit_semantic_analysis" title="Explicit semantic analysis">Explicit semantic analysis</a></li> <li><a href="/wiki/FastText" title="FastText">fastText</a></li> <li><a href="/wiki/GloVe" title="GloVe">GloVe</a></li> <li><a href="/wiki/Language_model" title="Language model">Language model</a> (<a href="/wiki/Large_language_model" title="Large language model">large</a>)</li> <li><a href="/wiki/Latent_semantic_analysis" title="Latent semantic analysis">Latent semantic analysis</a></li> <li><a href="/wiki/Seq2seq" title="Seq2seq">Seq2seq</a></li> <li><a href="/wiki/Word_embedding" title="Word embedding">Word embedding</a></li> <li><a href="/wiki/Word2vec" title="Word2vec">Word2vec</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Language_resource" title="Language resource">Language resources</a>,<br />datasets and corpora</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"></div><table class="nowraplinks navbox-subgroup" style="border-spacing:0"><tbody><tr><th scope="row" class="navbox-group" style="width:1%">Types and<br />standards</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Corpus_linguistics" title="Corpus linguistics">Corpus linguistics</a></li> <li><a href="/wiki/Lexical_resource" title="Lexical resource">Lexical resource</a></li> <li><a href="/wiki/Linguistic_Linked_Open_Data" title="Linguistic Linked Open Data">Linguistic Linked Open Data</a></li> <li><a href="/wiki/Machine-readable_dictionary" title="Machine-readable dictionary">Machine-readable dictionary</a></li> <li><a href="/wiki/Parallel_text" title="Parallel text">Parallel text</a></li> <li><a href="/wiki/PropBank" title="PropBank">PropBank</a></li> <li><a href="/wiki/Semantic_network" title="Semantic network">Semantic network</a></li> <li><a href="/wiki/Simple_Knowledge_Organization_System" title="Simple Knowledge Organization System">Simple Knowledge Organization System</a></li> <li><a href="/wiki/Speech_corpus" title="Speech corpus">Speech corpus</a></li> <li><a href="/wiki/Text_corpus" title="Text corpus">Text corpus</a></li> <li><a href="/wiki/Thesaurus_(information_retrieval)" title="Thesaurus (information retrieval)">Thesaurus (information retrieval)</a></li> <li><a href="/wiki/Treebank" title="Treebank">Treebank</a></li> <li><a href="/wiki/Universal_Dependencies" title="Universal Dependencies">Universal Dependencies</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Data</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/BabelNet" title="BabelNet">BabelNet</a></li> <li><a href="/wiki/Bank_of_English" title="Bank of English">Bank of English</a></li> <li><a href="/wiki/DBpedia" title="DBpedia">DBpedia</a></li> <li><a href="/wiki/FrameNet" title="FrameNet">FrameNet</a></li> <li><a href="/wiki/Google_Ngram_Viewer" class="mw-redirect" title="Google Ngram Viewer">Google Ngram Viewer</a></li> <li><a href="/wiki/UBY" title="UBY">UBY</a></li> <li><a href="/wiki/WordNet" title="WordNet">WordNet</a></li> <li><a href="/wiki/Wikidata" title="Wikidata">Wikidata</a></li></ul> </div></td></tr></tbody></table><div></div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Automatic_identification_and_data_capture" title="Automatic identification and data capture">Automatic identification<br />and data capture</a></th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Speech_recognition" title="Speech recognition">Speech recognition</a></li> <li><a href="/wiki/Speech_segmentation" title="Speech segmentation">Speech segmentation</a></li> <li><a class="mw-selflink selflink">Speech synthesis</a></li> <li><a href="/wiki/Natural_language_generation" title="Natural language generation">Natural language generation</a></li> <li><a href="/wiki/Optical_character_recognition" title="Optical character recognition">Optical character recognition</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Topic_model" title="Topic model">Topic model</a></th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Document_classification" title="Document classification">Document classification</a></li> <li><a href="/wiki/Latent_Dirichlet_allocation" title="Latent Dirichlet allocation">Latent Dirichlet allocation</a></li> <li><a href="/wiki/Pachinko_allocation" title="Pachinko allocation">Pachinko allocation</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Computer-assisted_reviewing" title="Computer-assisted reviewing">Computer-assisted<br />reviewing</a></th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Automated_essay_scoring" title="Automated essay scoring">Automated essay scoring</a></li> <li><a href="/wiki/Concordancer" title="Concordancer">Concordancer</a></li> <li><a href="/wiki/Grammar_checker" title="Grammar checker">Grammar checker</a></li> <li><a href="/wiki/Predictive_text" title="Predictive text">Predictive text</a></li> <li><a href="/wiki/Pronunciation_assessment" title="Pronunciation assessment">Pronunciation assessment</a></li> <li><a href="/wiki/Spell_checker" title="Spell checker">Spell checker</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%"><a href="/wiki/Natural-language_user_interface" title="Natural-language user interface">Natural language<br />user interface</a></th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Chatbot" title="Chatbot">Chatbot</a></li> <li><a href="/wiki/Interactive_fiction" title="Interactive fiction">Interactive fiction</a> (c.f. <a href="/wiki/Syntax_guessing" class="mw-redirect" title="Syntax guessing">Syntax guessing</a>)</li> <li><a href="/wiki/Question_answering" title="Question answering">Question answering</a></li> <li><a href="/wiki/Virtual_assistant" title="Virtual assistant">Virtual assistant</a></li> <li><a href="/wiki/Voice_user_interface" title="Voice user interface">Voice user interface</a></li></ul> </div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Related</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"> <ul><li><a href="/wiki/Formal_semantics_(natural_language)" title="Formal semantics (natural language)">Formal semantics</a></li> <li><a href="/wiki/Hallucination_(artificial_intelligence)" title="Hallucination (artificial intelligence)">Hallucination</a></li> <li><a href="/wiki/Natural_Language_Toolkit" title="Natural Language Toolkit">Natural Language Toolkit</a></li> <li><a href="/wiki/SpaCy" title="SpaCy">spaCy</a></li></ul> </div></td></tr></tbody></table></div> <div class="navbox-styles"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1129693374"><link rel="mw-deduplicated-inline-style" href="mw-data:TemplateStyles:r1236075235"><style data-mw-deduplicate="TemplateStyles:r1038841319">.mw-parser-output .tooltip-dotted{border-bottom:1px dotted;cursor:help}</style></div><div role="navigation" class="navbox authority-control" aria-labelledby="Authority_control_databases_frameless&#124;text-top&#124;10px&#124;alt=Edit_this_at_Wikidata&#124;link=https&#58;//www.wikidata.org/wiki/Q16346#identifiers&#124;class=noprint&#124;Edit_this_at_Wikidata" style="padding:3px"><table class="nowraplinks hlist mw-collapsible autocollapse navbox-inner" style="border-spacing:0;background:transparent;color:inherit"><tbody><tr><th scope="col" class="navbox-title" colspan="2"><div id="Authority_control_databases_frameless&#124;text-top&#124;10px&#124;alt=Edit_this_at_Wikidata&#124;link=https&#58;//www.wikidata.org/wiki/Q16346#identifiers&#124;class=noprint&#124;Edit_this_at_Wikidata" style="font-size:114%;margin:0 4em"><a href="/wiki/Help:Authority_control" title="Help:Authority control">Authority control databases</a> <span class="mw-valign-text-top noprint" typeof="mw:File/Frameless"><a href="https://www.wikidata.org/wiki/Q16346#identifiers" title="Edit this at Wikidata"><img alt="Edit this at Wikidata" src="//upload.wikimedia.org/wikipedia/en/thumb/8/8a/OOjs_UI_icon_edit-ltr-progressive.svg/10px-OOjs_UI_icon_edit-ltr-progressive.svg.png" decoding="async" width="10" height="10" class="mw-file-element" srcset="//upload.wikimedia.org/wikipedia/en/thumb/8/8a/OOjs_UI_icon_edit-ltr-progressive.svg/15px-OOjs_UI_icon_edit-ltr-progressive.svg.png 1.5x, //upload.wikimedia.org/wikipedia/en/thumb/8/8a/OOjs_UI_icon_edit-ltr-progressive.svg/20px-OOjs_UI_icon_edit-ltr-progressive.svg.png 2x" data-file-width="20" data-file-height="20" /></a></span></div></th></tr><tr><th scope="row" class="navbox-group" style="width:1%">National</th><td class="navbox-list-with-group navbox-list navbox-odd" style="width:100%;padding:0"><div style="padding:0 0.25em"><ul><li><span class="uid"><a rel="nofollow" class="external text" href="https://id.ndl.go.jp/auth/ndlna/00575464">Japan</a></span></li><li><span class="uid"><span class="rt-commentedText tooltip tooltip-dotted" title="syntéza řeči"><a rel="nofollow" class="external text" href="https://aleph.nkp.cz/F/?func=find-c&local_base=aut&ccl_term=ica=ph351275&CON_LNG=ENG">Czech Republic</a></span></span></li><li><span class="uid"><a rel="nofollow" class="external text" href="http://olduli.nli.org.il/F/?func=find-b&local_base=NLX10&find_code=UID&request=987007565841305171">Israel</a></span></li></ul></div></td></tr><tr><th scope="row" class="navbox-group" style="width:1%">Other</th><td class="navbox-list-with-group navbox-list navbox-even" style="width:100%;padding:0"><div style="padding:0 0.25em"><ul><li><span class="uid"><a rel="nofollow" class="external text" href="https://musicbrainz.org/instrument/b0f83029-6d38-4f6f-bd30-db44e427f497">MusicBrainz instrument</a></span></li></ul></div></td></tr></tbody></table></div></div><noscript><img src="https://login.wikimedia.org/wiki/Special:CentralAutoLogin/start?type=1x1" alt="" width="1" height="1" style="border: none; position: absolute;"></noscript> <div class="printfooter" data-nosnippet="">Retrieved from "<a dir="ltr" href="https://en.wikipedia.org/w/index.php?title=Speech_synthesis&oldid=1259199237">https://en.wikipedia.org/w/index.php?title=Speech_synthesis&oldid=1259199237</a>"</div></div> <div id="catlinks" class="catlinks" data-mw="interface"><div id="mw-normal-catlinks" class="mw-normal-catlinks"><a href="/wiki/Help:Category" title="Help:Category">Categories</a>: <ul><li><a href="/wiki/Category:Speech_synthesis" title="Category:Speech synthesis">Speech synthesis</a></li><li><a href="/wiki/Category:Applications_of_artificial_intelligence" title="Category:Applications of artificial intelligence">Applications of artificial intelligence</a></li><li><a href="/wiki/Category:Assistive_technology" title="Category:Assistive technology">Assistive technology</a></li><li><a href="/wiki/Category:Auditory_displays" title="Category:Auditory displays">Auditory displays</a></li><li><a href="/wiki/Category:Computational_linguistics" title="Category:Computational linguistics">Computational linguistics</a></li><li><a href="/wiki/Category:History_of_human%E2%80%93computer_interaction" title="Category:History of human–computer interaction">History of human–computer interaction</a></li></ul></div><div id="mw-hidden-catlinks" class="mw-hidden-catlinks mw-hidden-cats-hidden">Hidden categories: <ul><li><a href="/wiki/Category:Articles_with_German-language_sources_(de)" title="Category:Articles with German-language sources (de)">Articles with German-language sources (de)</a></li><li><a href="/wiki/Category:Webarchive_template_wayback_links" title="Category:Webarchive template wayback links">Webarchive template wayback links</a></li><li><a href="/wiki/Category:All_articles_with_dead_external_links" title="Category:All articles with dead external links">All articles with dead external links</a></li><li><a href="/wiki/Category:Articles_with_dead_external_links_from_December_2011" title="Category:Articles with dead external links from December 2011">Articles with dead external links from December 2011</a></li><li><a href="/wiki/Category:CS1_maint:_date_and_year" title="Category:CS1 maint: date and year">CS1 maint: date and year</a></li><li><a href="/wiki/Category:CS1_Polish-language_sources_(pl)" title="Category:CS1 Polish-language sources (pl)">CS1 Polish-language sources (pl)</a></li><li><a href="/wiki/Category:Articles_with_short_description" title="Category:Articles with short description">Articles with short description</a></li><li><a href="/wiki/Category:Short_description_matches_Wikidata" title="Category:Short description matches Wikidata">Short description matches Wikidata</a></li><li><a href="/wiki/Category:Wikipedia_pending_changes_protected_pages" title="Category:Wikipedia pending changes protected pages">Wikipedia pending changes protected pages</a></li><li><a href="/wiki/Category:Articles_with_hAudio_microformats" title="Category:Articles with hAudio microformats">Articles with hAudio microformats</a></li><li><a href="/wiki/Category:All_articles_with_unsourced_statements" title="Category:All articles with unsourced statements">All articles with unsourced statements</a></li><li><a href="/wiki/Category:Articles_with_unsourced_statements_from_September_2024" title="Category:Articles with unsourced statements from September 2024">Articles with unsourced statements from September 2024</a></li><li><a href="/wiki/Category:Pages_with_plain_IPA" title="Category:Pages with plain IPA">Pages with plain IPA</a></li><li><a href="/wiki/Category:Articles_with_unsourced_statements_from_April_2016" title="Category:Articles with unsourced statements from April 2016">Articles with unsourced statements from April 2016</a></li><li><a href="/wiki/Category:All_articles_lacking_reliable_references" title="Category:All articles lacking reliable references">All articles lacking reliable references</a></li><li><a href="/wiki/Category:Articles_lacking_reliable_references_from_July_2019" title="Category:Articles lacking reliable references from July 2019">Articles lacking reliable references from July 2019</a></li><li><a href="/wiki/Category:Articles_containing_potentially_dated_statements_from_2016" title="Category:Articles containing potentially dated statements from 2016">Articles containing potentially dated statements from 2016</a></li><li><a href="/wiki/Category:All_articles_containing_potentially_dated_statements" title="Category:All articles containing potentially dated statements">All articles containing potentially dated statements</a></li><li><a href="/wiki/Category:Articles_with_unsourced_statements_from_January_2012" title="Category:Articles with unsourced statements from January 2012">Articles with unsourced statements from January 2012</a></li><li><a href="/wiki/Category:Articles_with_unsourced_statements_from_February_2007" title="Category:Articles with unsourced statements from February 2007">Articles with unsourced statements from February 2007</a></li><li><a href="/wiki/Category:Articles_with_excerpts" title="Category:Articles with excerpts">Articles with excerpts</a></li><li><a href="/wiki/Category:Articles_needing_additional_references_from_April_2023" title="Category:Articles needing additional references from April 2023">Articles needing additional references from April 2023</a></li><li><a href="/wiki/Category:All_articles_needing_additional_references" title="Category:All articles needing additional references">All articles needing additional references</a></li><li><a href="/wiki/Category:Articles_with_unsourced_statements_from_April_2020" title="Category:Articles with unsourced statements from April 2020">Articles with unsourced statements from April 2020</a></li><li><a href="/wiki/Category:Articles_with_unsourced_statements_from_January_2022" title="Category:Articles with unsourced statements from January 2022">Articles with unsourced statements from January 2022</a></li><li><a href="/wiki/Category:Articles_with_unsourced_statements_from_June_2024" title="Category:Articles with unsourced statements from June 2024">Articles with unsourced statements from June 2024</a></li><li><a href="/wiki/Category:Commons_category_link_from_Wikidata" title="Category:Commons category link from Wikidata">Commons category link from Wikidata</a></li></ul></div></div> </div> </main> </div> <div class="mw-footer-container"> <footer id="footer" class="mw-footer" > <ul id="footer-info"> <li id="footer-info-lastmod"> This page was last edited on 23 November 2024, at 22:27<span class="anonymous-show"> (UTC)</span>.</li> <li id="footer-info-copyright">Text is available under the <a href="/wiki/Wikipedia:Text_of_the_Creative_Commons_Attribution-ShareAlike_4.0_International_License" title="Wikipedia:Text of the Creative Commons Attribution-ShareAlike 4.0 International License">Creative Commons Attribution-ShareAlike 4.0 License</a>; additional terms may apply. By using this site, you agree to the <a href="https://foundation.wikimedia.org/wiki/Special:MyLanguage/Policy:Terms_of_Use" class="extiw" title="foundation:Special:MyLanguage/Policy:Terms of Use">Terms of Use</a> and <a href="https://foundation.wikimedia.org/wiki/Special:MyLanguage/Policy:Privacy_policy" class="extiw" title="foundation:Special:MyLanguage/Policy:Privacy policy">Privacy Policy</a>. Wikipedia® is a registered trademark of the <a rel="nofollow" class="external text" href="https://wikimediafoundation.org/">Wikimedia Foundation, Inc.</a>, a non-profit organization.</li> </ul> <ul id="footer-places"> <li id="footer-places-privacy"><a href="https://foundation.wikimedia.org/wiki/Special:MyLanguage/Policy:Privacy_policy">Privacy policy</a></li> <li id="footer-places-about"><a href="/wiki/Wikipedia:About">About Wikipedia</a></li> <li id="footer-places-disclaimers"><a href="/wiki/Wikipedia:General_disclaimer">Disclaimers</a></li> <li id="footer-places-contact"><a href="//en.wikipedia.org/wiki/Wikipedia:Contact_us">Contact Wikipedia</a></li> <li id="footer-places-wm-codeofconduct"><a href="https://foundation.wikimedia.org/wiki/Special:MyLanguage/Policy:Universal_Code_of_Conduct">Code of Conduct</a></li> <li id="footer-places-developers"><a href="https://developer.wikimedia.org">Developers</a></li> <li id="footer-places-statslink"><a href="https://stats.wikimedia.org/#/en.wikipedia.org">Statistics</a></li> <li id="footer-places-cookiestatement"><a href="https://foundation.wikimedia.org/wiki/Special:MyLanguage/Policy:Cookie_statement">Cookie statement</a></li> <li id="footer-places-mobileview"><a href="//en.m.wikipedia.org/w/index.php?title=Speech_synthesis&mobileaction=toggle_view_mobile" class="noprint stopMobileRedirectToggle">Mobile view</a></li> </ul> <ul id="footer-icons" class="noprint"> <li id="footer-copyrightico"><a href="https://wikimediafoundation.org/" class="cdx-button cdx-button--fake-button cdx-button--size-large cdx-button--fake-button--enabled"><img src="/static/images/footer/wikimedia-button.svg" width="84" height="29" alt="Wikimedia Foundation" loading="lazy"></a></li> <li id="footer-poweredbyico"><a href="https://www.mediawiki.org/" class="cdx-button cdx-button--fake-button cdx-button--size-large cdx-button--fake-button--enabled"><img src="/w/resources/assets/poweredby_mediawiki.svg" alt="Powered by MediaWiki" width="88" height="31" loading="lazy"></a></li> </ul> </footer> </div> </div> </div> <div class="vector-settings" id="p-dock-bottom"> <ul></ul> </div><script>(RLQ=window.RLQ||[]).push(function(){mw.config.set({"wgHostname":"mw-web.codfw.canary-6cd999d6b6-2sp2r","wgBackendResponseTime":176,"wgPageParseReport":{"limitreport":{"cputime":"1.649","walltime":"1.953","ppvisitednodes":{"value":9110,"limit":1000000},"postexpandincludesize":{"value":303490,"limit":2097152},"templateargumentsize":{"value":10330,"limit":2097152},"expansiondepth":{"value":17,"limit":100},"expensivefunctioncount":{"value":27,"limit":500},"unstrip-depth":{"value":1,"limit":20},"unstrip-size":{"value":377898,"limit":5000000},"entityaccesscount":{"value":1,"limit":400},"timingprofile":["100.00% 1635.293 1 -total"," 48.22% 788.528 1 Template:Reflist"," 13.77% 225.129 2 Template:Excerpt"," 9.16% 149.868 36 Template:Cite_web"," 8.95% 146.346 14 Template:Cite_book"," 7.12% 116.474 1 Template:In_lang"," 6.48% 106.018 10 Template:Citation_needed"," 6.44% 105.322 12 Template:Fix"," 5.64% 92.272 17 Template:Cite_journal"," 5.37% 87.795 1 Template:Artificial_intelligence"]},"scribunto":{"limitreport-timeusage":{"value":"1.054","limit":"10.000"},"limitreport-memusage":{"value":16680786,"limit":52428800},"limitreport-profile":[["MediaWiki\\Extension\\Scribunto\\Engines\\LuaSandbox\\LuaSandboxCallback::callParserFunction","260","22.0"],["?","200","16.9"],["recursiveClone \u003CmwInit.lua:45\u003E","120","10.2"],["MediaWiki\\Extension\\Scribunto\\Engines\\LuaSandbox\\LuaSandboxCallback::find","120","10.2"],["MediaWiki\\Extension\\Scribunto\\Engines\\LuaSandbox\\LuaSandboxCallback::getExpensiveData","60","5.1"],["init \u003CModule:Citation/CS1/Date_validation\u003E","40","3.4"],["\u003Cmw.lua:694\u003E","40","3.4"],["dataWrapper \u003Cmw.lua:672\u003E","40","3.4"],["type","40","3.4"],["MediaWiki\\Extension\\Scribunto\\Engines\\LuaSandbox\\LuaSandboxCallback::getExpandedArgument","40","3.4"],["[others]","220","18.6"]]},"cachereport":{"origin":"mw-web.codfw.main-57488d5c7d-4qxh9","timestamp":"20241128020211","ttl":2592000,"transientcontent":false}}});});</script> <script type="application/ld+json">{"@context":"https:\/\/schema.org","@type":"Article","name":"Speech synthesis","url":"https:\/\/en.wikipedia.org\/wiki\/Speech_synthesis","sameAs":"http:\/\/www.wikidata.org\/entity\/Q16346","mainEntity":"http:\/\/www.wikidata.org\/entity\/Q16346","author":{"@type":"Organization","name":"Contributors to Wikimedia projects"},"publisher":{"@type":"Organization","name":"Wikimedia Foundation, Inc.","logo":{"@type":"ImageObject","url":"https:\/\/www.wikimedia.org\/static\/images\/wmf-hor-googpub.png"}},"datePublished":"2002-03-04T15:36:04Z","headline":"artificial production of human speech"}</script> </body> </html>