{"id":5531,"date":"2017-05-30T18:34:26","date_gmt":"2017-05-31T01:34:26","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=5531"},"modified":"2017-05-30T18:34:26","modified_gmt":"2017-05-31T01:34:26","slug":"ai-computers-learn-to-fake-human-speech-detect-other-fakes","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2017\/05\/30\/ai-computers-learn-to-fake-human-speech-detect-other-fakes\/","title":{"rendered":"AI: Computers learn to fake human speech, detect other fakes"},"content":{"rendered":"<p>Baidu\u2019s\u00a0<a href=\"http:\/\/research.baidu.com\/deep-voice-2-multi-speaker-neural-text-speech\/\">Deep Voice 2<\/a>\u00a0can eerily render sentences with numerous accents &amp; other unique quirks; click through to hear examples.<\/p>\n<blockquote>\n<p>In only three months, we\u2019ve been able to scale our system from 20 hours of speech and a single voice to <em>hundreds<\/em> of hours with <em>hundreds<\/em> of voices. Deep Voice 2 can learn from hundreds of voices and imitate them perfectly. Unlike traditional systems, which need dozens of hours of audio from a single speaker, Deep Voice 2 can learn from hundreds of unique voices from less than half an hour of data per speaker, while achieving high audio quality.\u00a0<\/p>\n<\/blockquote>\n<p>Conversely, <a href=\"https:\/\/rnd.dt.com.au\/anti-ai-ai-a-wearable-ai-device-244900e4d71c\">Anti AI AI<\/a>\u00a0is a wearable detector of synthetic voices:<\/p>\n<blockquote>\n<p>The device notifies the wearer when a synthetic voice is detected and cools the skin using a thermoelectric plate to alert the wearer the voice they are hearing was synthesised: by a cold, lifeless machine.<\/p>\n<\/blockquote>\n<p>To quote the stoney falsetto of Towlie, <em>\u201cI have no idea what\u2019s goin\u2019 on right now\u2026\u201d<\/em><\/p>\n<p><img decoding=\"async\" loading=\"lazy\" title=\"NewImage.png\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2017\/05\/NewImage-35.png\" alt=\"NewImage\" width=\"600\" height=\"337\" border=\"0\" \/><\/p>\n<p>[Via <a href=\"https:\/\/plus.google.com\/+WayneRadinsky\">Wayne Radinsky<\/a>]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Baidu\u2019s\u00a0Deep Voice 2\u00a0can eerily render sentences with numerous accents &amp; other unique quirks; click through to hear examples. In only three months, we\u2019ve been able to scale our system from 20 hours of speech and a single voice to hundreds of hours with hundreds of voices. Deep Voice 2 can learn from hundreds of voices [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[8],"tags":[],"_links":{"self":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/5531"}],"collection":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/comments?post=5531"}],"version-history":[{"count":1,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/5531\/revisions"}],"predecessor-version":[{"id":5532,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/5531\/revisions\/5532"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=5531"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=5531"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=5531"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}