{"id":7762,"date":"2023-01-19T19:14:12","date_gmt":"2023-01-20T02:14:12","guid":{"rendered":"https:\/\/mattfife.com\/?p=7762"},"modified":"2023-01-22T12:14:23","modified_gmt":"2023-01-22T19:14:23","slug":"microsoft-can-synthesize-your-voice-with-just-a-3-second-clip","status":"publish","type":"post","link":"https:\/\/mattfife.com\/?p=7762","title":{"rendered":"Microsoft can synthesize your voice with just a 3 second clip"},"content":{"rendered":"\n<p>Microsoft researchers announced a new text-to-speech AI model called\u00a0<a href=\"https:\/\/valle-demo.github.io\/\">VALL-E<\/a>\u00a0that can closely simulate a person&#8217;s voice when given a three-second audio sample. Once it learns a specific voice, VALL-E can synthesize audio of that person saying anything\u2014and do it in a way that attempts to preserve the speaker&#8217;s emotional tone and background environmental noise balance.<\/p>\n\n\n\n<p>The scientists also note that since VALL-E could synthesize speech that maintains speaker identity, it may carry potential risks in misuse of the model, such as spoofing voice identification or impersonating a specific speaker. <\/p>\n\n\n\n<p><a href=\"https:\/\/valle-demo.github.io\/\" data-type=\"URL\" data-id=\"https:\/\/valle-demo.github.io\/\" target=\"_blank\" rel=\"noreferrer noopener\">You can find audio samples and the paper here<\/a>.<\/p>\n\n\n\n<p>It sure would make breaking into Werner Brandes office a lot easier (1992 movie <em>Sneakers<\/em>) than convincing your friend to record snippets of a really terrible date.<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<span class=\"embed-youtube\" style=\"text-align:center; display: block;\"><iframe loading=\"lazy\" class=\"youtube-player\" width=\"640\" height=\"360\" src=\"https:\/\/www.youtube.com\/embed\/-zVgWpVXb64?version=3&#038;rel=1&#038;showsearch=0&#038;showinfo=1&#038;iv_load_policy=1&#038;fs=1&#038;hl=en-US&#038;autohide=2&#038;wmode=transparent\" allowfullscreen=\"true\" style=\"border:0;\" sandbox=\"allow-scripts allow-same-origin allow-popups allow-presentation allow-popups-to-escape-sandbox\"><\/iframe><\/span>\n<\/div><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Microsoft researchers announced a new text-to-speech AI model called\u00a0VALL-E\u00a0that can closely simulate a person&#8217;s voice when given a three-second audio sample. Once it learns a specific voice, VALL-E can synthesize audio of that person saying anything\u2014and do it in a way that attempts to preserve the speaker&#8217;s emotional tone and background environmental noise balance. The scientists also note that since VALL-E could synthesize speech that maintains speaker identity, it may carry potential risks in misuse of the model, such as&#8230;<\/p>\n<p class=\"read-more\"><a class=\"btn btn-default\" href=\"https:\/\/mattfife.com\/?p=7762\"> Read More<span class=\"screen-reader-text\">  Read More<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[28,9],"tags":[],"class_list":["post-7762","post","type-post","status-publish","format-standard","hentry","category-ai","category-cool"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p4WECr-21c","jetpack-related-posts":[],"_links":{"self":[{"href":"https:\/\/mattfife.com\/index.php?rest_route=\/wp\/v2\/posts\/7762","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mattfife.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mattfife.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mattfife.com\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mattfife.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=7762"}],"version-history":[{"count":1,"href":"https:\/\/mattfife.com\/index.php?rest_route=\/wp\/v2\/posts\/7762\/revisions"}],"predecessor-version":[{"id":7763,"href":"https:\/\/mattfife.com\/index.php?rest_route=\/wp\/v2\/posts\/7762\/revisions\/7763"}],"wp:attachment":[{"href":"https:\/\/mattfife.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7762"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mattfife.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7762"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mattfife.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7762"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}