{"id":5631,"date":"2017-06-27T06:01:44","date_gmt":"2017-06-27T13:01:44","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=5631"},"modified":"2017-06-27T06:01:44","modified_gmt":"2017-06-27T13:01:44","slug":"a-closer-look-at-adobes-audio-photoshopping","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2017\/06\/27\/a-closer-look-at-adobes-audio-photoshopping\/","title":{"rendered":"A closer look at Adobe&#8217;s \u201cAudio Photoshopping\u201d"},"content":{"rendered":"<p><em>Pandora, your box is rustling<\/em>\u2026<\/p>\n<p>Last fall Adobe gave a <a href=\"http:\/\/jnack.com\/blog\/2016\/11\/08\/audio-photoshopping\/\">sneak preview<\/a> of \u201cVoCo,\u201d its audio witchcraft tech that can replace speech with synthesized voices, doing so radically faster &amp; more accurately than trained human editors can. It seems scary-good\u2014emphasis on scary. Check out <a href=\"http:\/\/gfx.cs.princeton.edu\/pubs\/Jin_2017_VTI\/\">the paper<\/a> and this demo:<\/p>\n<p><iframe loading=\"lazy\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/RB7upq8nzIU?feature=oembed\" frameborder=\"0\" allow=\"autoplay; encrypted-media\" allowfullscreen><\/iframe><\/p>\n<p>Theoretically related: <a href=\"http:\/\/jnack.com\/blog\/2017\/05\/30\/ai-computers-learn-to-fake-human-speech-detect-other-fakes\/\">Deep Voice and Anti AI AI<\/a>.<\/p>\n<p><img decoding=\"async\" loading=\"lazy\" title=\"NewImage.png\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2017\/06\/NewImage-26.png\" alt=\"NewImage\" width=\"600\" height=\"109\" border=\"0\" \/><\/p>\n<p>[<a href=\"https:\/\/www.youtube.com\/watch?v=RB7upq8nzIU\">YouTube<\/a>]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Pandora, your box is rustling\u2026 Last fall Adobe gave a sneak preview of \u201cVoCo,\u201d its audio witchcraft tech that can replace speech with synthesized voices, doing so radically faster &amp; more accurately than trained human editors can. It seems scary-good\u2014emphasis on scary. Check out the paper and this demo: Theoretically related: Deep Voice and Anti [&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\/5631"}],"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=5631"}],"version-history":[{"count":1,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/5631\/revisions"}],"predecessor-version":[{"id":5632,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/5631\/revisions\/5632"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=5631"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=5631"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=5631"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}