{"id":155015,"date":"2023-01-09T20:25:32","date_gmt":"2023-01-10T02:25:32","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2023\/01\/this-new-ai-can-mimic-human-voices-with-only-3-seconds-of-training"},"modified":"2023-01-09T20:25:32","modified_gmt":"2023-01-10T02:25:32","slug":"this-new-ai-can-mimic-human-voices-with-only-3-seconds-of-training","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2023\/01\/this-new-ai-can-mimic-human-voices-with-only-3-seconds-of-training","title":{"rendered":"This new AI can mimic human voices with only 3 seconds of training"},"content":{"rendered":"<p><\/p>\n<p><iframe style=\"display: block; margin: 0 auto; width: 100%; aspect-ratio: 4\/3; object-fit: contain;\" src=\"https:\/\/www.youtube.com\/embed\/MT_u9Rurrqg?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope;\n   picture-in-picture\" allowfullscreen><\/iframe><\/p>\n<p>Humanity has taken yet another step toward the inevitable war against the machines (which we will lose) with the creation of Vall-E, an AI developed by a team of researchers at Microsoft that can produce high quality human voice replications with only a few seconds of audio training.<\/p>\n<p>Vall-E isn\u2019t the first AI-powered voice tool\u2014 <a href=\"https:\/\/www.pcgamer.com\/this-fan-made-skyrim-trailer-uses-entirely-ai-synthesized-voice-acting\/\" target=\"_blank\" rel=\"noopener\" class=\"\">xVASynth<\/a> (opens in new tab), for instance, has been kicking around for a couple years now\u2014but it promises to exceed them all in terms of pure capability. In a paper available at <a href=\"https:\/\/arxiv.org\/abs\/2301.02111\" target=\"_blank\" rel=\"noopener\" class=\"\">Cornell University<\/a> (opens in new tab) (via <a href=\"https:\/\/www.windowscentral.com\/software-apps\/microsofts-vall-e-can-imitate-any-voice-with-just-a-three-second-sample\" target=\"_blank\" rel=\"noopener\" class=\"\">Windows Central<\/a> (opens in new tab) ), the Vall-E researchers say that most current text-to-speech systems are limited by their reliance on \u201chigh-quality clean data\u201d in order to accurately synthesize high-quality speech.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Humanity has taken yet another step toward the inevitable war against the machines (which we will lose) with the creation of Vall-E, an AI developed by a team of researchers at Microsoft that can produce high quality human voice replications with only a few seconds of audio training. Vall-E isn\u2019t the first AI-powered voice tool\u2014 [\u2026]<\/p>\n","protected":false},"author":359,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-155015","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/155015","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/359"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=155015"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/155015\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=155015"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=155015"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=155015"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}