{"id":19714,"date":"2017-12-24T05:42:59","date_gmt":"2017-12-24T03:42:59","guid":{"rendered":"http:\/\/www.kulturtechno.de\/?p=19714"},"modified":"2017-12-10T11:47:50","modified_gmt":"2017-12-10T09:47:50","slug":"stimm-font-aus-aufnahme-erstellen","status":"publish","type":"post","link":"https:\/\/www.kulturtechno.de\/?p=19714","title":{"rendered":"Stimm-Font aus Aufnahme erstellen"},"content":{"rendered":"<p>Die Software Lyrebird behauptet, sie k\u00f6nne aus nur einer Minute Stimmaufzeichnungen jegliche Formulierung und Intonation simulieren:<br \/>\n\u201eRecord 1 minute from someone&#8217;s voice and Lyrebird can compress her\/his voice&#8217;s DNA into a unique key. Use this key to generate anything with its corresponding voice\u201c. <\/p>\n<blockquote><p>Lyrebird will offer an API to copy the voice of anyone. It will need as little as one minute of audio recording of a speaker to compute a unique key defining her\/his voice. This key will then allow to generate anything from its corresponding voice. The API will be robust enough to learn from noisy recordings. The following sample illustrates this feature, the samples are not cherry-picked. <\/p><\/blockquote>\n<p><iframe loading=\"lazy\" width=\"100%\" height=\"300\" scrolling=\"no\" frameborder=\"no\" src=\"https:\/\/w.soundcloud.com\/player\/?url=https%3A\/\/api.soundcloud.com\/tracks\/318661840&amp;color=%23ff5500&amp;auto_play=false&amp;hide_related=false&amp;show_comments=true&amp;show_user=true&amp;show_reposts=false&amp;show_teaser=true&amp;visual=true\"><\/iframe><\/p>\n<p>Die Probleme, die das reibungslose Kopieren von Stimmen mit sich bringt, liegen auf der Hand und die InfoSec-Bruhahas sind nur die offensichtlichsten davon:<\/p>\n<blockquote><p>    Researchers at the University of Alabama, Birmingham, led by Nitesh Saxena, were able to use Festvox to clone voices based on only five minutes of speech retrieved online. When tested against voice-biometrics software like that used by many banks to block unauthorised access to accounts, more than 80% of the fake voices tricked the computer. Alan Black, one of Festvox\u2019s developers, reckons systems that rely on voice-ID software are now \u201cdeeply, fundamentally insecure\u201d.\n<\/p><\/blockquote>\n<p>Die Entwickler von Lyrebird sind sich der Probleme ihrer Technologie bewusst, Snip von der Ethics-Section ihrer Website:<\/p>\n<blockquote><p>    Voice recordings are currently considered as strong pieces of evidence in our societies and in particular in jurisdictions of many countries. Our technology questions the validity of such evidence as it allows to easily manipulate audio recordings. This could potentially have dangerous consequences such as misleading diplomats, fraud and more generally any other problem caused by stealing the identity of someone else.<\/p>\n<p>    By releasing our technology publicly and making it available to anyone, we want to ensure that there will be no such risks. We hope that everyone will soon be aware that such technology exists and that copying the voice of someone else is possible. More generally, we want to raise attention ab<\/p><\/blockquote>\n<p>Ob das nun scary ist oder nur ein im Grunde bekannter Gag, wie seit jeher Stimmimitatoren ihren Ulk betreiben, we&#8217;ll see. Verbunden mit der <a href=\"http:\/\/www.kulturtechno.de\/?p=19690\">Lippensync-Technik <\/a>k\u00f6nnte es schon ein weiterer Schritt sein in die Ununterscheidbarkeit von Realit\u00e4t und Fiktion.<\/p>\n<p>(via <a href=\"http:\/\/www.nerdcore.de\/2017\/04\/26\/ai-voice-cloning\/?utm_source=feedburner&#038;utm_medium=feed&#038;utm_campaign=Feed%3A+NerdcoreRSS2+(Nerdcore)\">Nerdcore<\/a>)<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Die Software Lyrebird behauptet, sie k\u00f6nne aus nur einer Minute Stimmaufzeichnungen jegliche Formulierung und Intonation simulieren: \u201eRecord 1 minute from someone&#8217;s voice and Lyrebird can compress her\/his voice&#8217;s DNA into a unique key. Use this key to generate anything with its corresponding voice\u201c. Lyrebird will offer an API to copy the voice of anyone. It [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_links_to":"","_links_to_target":"","footnotes":""},"categories":[5],"tags":[],"class_list":["post-19714","post","type-post","status-publish","format-standard","hentry","category-technologik"],"_links":{"self":[{"href":"https:\/\/www.kulturtechno.de\/index.php?rest_route=\/wp\/v2\/posts\/19714"}],"collection":[{"href":"https:\/\/www.kulturtechno.de\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kulturtechno.de\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kulturtechno.de\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kulturtechno.de\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=19714"}],"version-history":[{"count":2,"href":"https:\/\/www.kulturtechno.de\/index.php?rest_route=\/wp\/v2\/posts\/19714\/revisions"}],"predecessor-version":[{"id":19716,"href":"https:\/\/www.kulturtechno.de\/index.php?rest_route=\/wp\/v2\/posts\/19714\/revisions\/19716"}],"wp:attachment":[{"href":"https:\/\/www.kulturtechno.de\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=19714"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kulturtechno.de\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=19714"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kulturtechno.de\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=19714"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}