{"id":182031,"date":"2023-01-09T23:21:59","date_gmt":"2023-01-09T23:21:59","guid":{"rendered":"https:\/\/harchi90.com\/microsofts-new-ai-can-simulate-anyones-voice-with-3-seconds-of-audio\/"},"modified":"2023-01-09T23:21:59","modified_gmt":"2023-01-09T23:21:59","slug":"microsofts-new-ai-can-simulate-anyones-voice-with-3-seconds-of-audio","status":"publish","type":"post","link":"https:\/\/harchi90.com\/microsofts-new-ai-can-simulate-anyones-voice-with-3-seconds-of-audio\/","title":{"rendered":"Microsoft&#8217;s new AI can simulate anyone&#8217;s voice with 3 seconds of audio"},"content":{"rendered":"<div itemprop=\"articleBody\">\n<figure class=\"intro-image intro-left\">\n  <figcaption class=\"caption\">\n<div class=\"caption-text\">enlarge <span class=\"sep\">\/<\/span> An AI-generated image of a person&#8217;s silhouette.<\/div>\n<p>Ars Technica<\/p>\n<\/figcaption><\/figure>\n<aside id=\"social-left\" class=\"social-left\" aria-label=\"Read the comments or share this article\">\n<\/aside>\n<p><!-- cache hit 73:single\/related:7cd5932fcf3a526398d8aa7bd55e8feb --><!-- empty --><\/p>\n<p>On Thursday, Microsoft researchers announced a new text-to-speech AI model called VALL-E that 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.<\/p>\n<p>Its creators speculate that VALL-E could be used for high-quality text-to-speech applications, speech editing where a recording of a person could be edited and changed from a text transcript (making them say something they originally didn&#8217;t), and audio content creation when combined with other generative AI models like GPT-3.<\/p>\n<p>Microsoft calls VALL-E a &#8220;neural codec language model,&#8221; and it builds off of a technology called EnCodec, which Meta announced in October 2022. Unlike other text-to-speech methods that typically synthesize speech by manipulating waveforms, VALL-E generates discrete audio codec codes from text and acoustic prompts.  It basically analyzes how a person sounds, breaks that information into discrete components (called &#8220;tokens&#8221;) thanks to EnCodec, and uses training data to match what it &#8220;knows&#8221; about how that voice would sound if it spoke other phrases outside of the three -second sample.  Or, as Microsoft puts it in the VALL-E paper:<\/p>\n<blockquote>\n<p>To synthesize personalized speech (eg, zero-shot TTS), VALL-E generates the corresponding acoustic tokens conditioned on the acoustic tokens of the 3-second enrolled recording and the phoneme prompt, which constrain the speaker and content information respectively.  Finally, the generated acoustic tokens are used to synthesize the final waveform with the corresponding neural codec decoder.<\/p>\n<\/blockquote>\n<p>Microsoft trained VALL-E&#8217;s speech synthesis capabilities on an audio library, assembled by Meta, called LibriLight.  It contains 60,000 hours of English language speech from more than 7,000 speakers, mostly pulled from LibriVox public domain audiobooks.  For VALL-E to generate a good result, the voice in the three-second sample must closely match a voice in the training data.<\/p>\n<aside class=\"ad_wrapper\" aria-label=\"In Content advertisement\">\n    <span class=\"ad_notice\">Advertisement <\/span>    <\/p>\n<\/aside>\n<p>On the VALL-E example website, Microsoft provides dozens of audio examples of the AI \u200b\u200bmodel in action.  Among the samples, the &#8220;Speaker Prompt&#8221; is the three-second audio provided to VALL-E that it must imitate.  The &#8220;Ground Truth&#8221; is a pre-existing recording of that same speaker saying a particular phrase for comparison purposes (sort of like the &#8220;control&#8221; in the experiment).  The &#8220;Baseline&#8221; is an example of synthesis provided by a conventional text-to-speech synthesis method, and the &#8220;VALL-E&#8221; sample is the output from the VALL-E model.<\/p>\n<figure class=\"image shortcode-img center large\" style=\"width:100%\"><img loading=\"lazy\" alt=\"A block diagram of VALL-E provided by Microsoft researchers.\" src=\"https:\/\/i0.wp.com\/cdn.arstechnica.net\/wp-content\/uploads\/2023\/01\/Overview-640x345.jpg?resize=640%2C345&#038;ssl=1\" width=\"640\" height=\"345\" srcset=\"https:\/\/cdn.arstechnica.net\/wp-content\/uploads\/2023\/01\/Overview.jpg 2x\" data-recalc-dims=\"1\"\/><figcaption class=\"caption\">\n<div class=\"caption-text\">enlarge <span class=\"sep\">\/<\/span> A block diagram of VALL-E provided by Microsoft researchers.<\/div>\n<p>Microsoft<\/p>\n<\/figcaption><\/figure>\n<p>While using VALL- to generate those results, the only E researchers fed the three-second &#8220;Speaker Prompt&#8221; sample and a text string (what they wanted the voice to say) into VALL-E.  So compare the &#8220;Ground Truth&#8221; sample to the &#8220;VALL-E&#8221; sample.  In some cases, the two samples are very close.  Some VALL-E results seem computer-generated, but others could potentially be mistaken for a human&#8217;s speech, which is the goal of the model.<\/p>\n<p>In addition to preserving a speaker&#8217;s vocal timbre and emotional tone, VALL-E can also imitate the &#8220;acoustic environment&#8221; of the sample audio.  For example, if the sample came from a telephone call, the audio output will simulate the acoustic and frequency properties of a telephone call in its synthesized output (that&#8217;s a fancy way of saying it will sound like a telephone call, too).  And Microsoft&#8217;s samples (in the &#8220;Synthesis of Diversity&#8221; section) demonstrate that VALL-E can generate variations in voice tone by changing the random seed used in the generation process.<\/p>\n<p>Perhaps owing to VALL-E&#8217;s ability to potentially fuel mischief and deception, Microsoft has not provided VALL-E code for others to experiment with, so we could not test VALL-E&#8217;s capabilities.  The researchers seem aware of the potential social harm that this technology could bring.  For the paper&#8217;s conclusion, they write:<\/p>\n<p>&#8220;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. To mitigate such risks, it is possible to build a detection model to discriminate whether an audio clip was synthesized by VALL-E. We will also put Microsoft AI Principles into practice when further developing the models.&#8221;<\/p>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"<p>enlarge \/ An AI-generated image of a person&#8217;s silhouette. Ars Technica On Thursday, Microsoft researchers announced a new text-to-speech AI model called VALL-E that 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 &hellip;<\/p>\n<p class=\"read-more\"> <a class=\"\" href=\"https:\/\/harchi90.com\/microsofts-new-ai-can-simulate-anyones-voice-with-3-seconds-of-audio\/\"> <span class=\"screen-reader-text\">Microsoft&#8217;s new AI can simulate anyone&#8217;s voice with 3 seconds of audio<\/span> Read More &raquo;<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"default","ast-global-header-display":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","jetpack_publicize_message":"","jetpack_is_tweetstorm":false,"jetpack_publicize_feature_enabled":true},"categories":[4],"tags":[],"jetpack_publicize_connections":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v19.10 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Microsoft&#039;s new AI can simulate anyone&#039;s voice with 3 seconds of audio - harchi90<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/news.google.com\/__i\/rss\/rd\/articles\/CBMifGh0dHBzOi8vYXJzdGVjaG5pY2EuY29tL2luZm9ybWF0aW9uLXRlY2hub2xvZ3kvMjAyMy8wMS9taWNyb3NvZnRzLW5ldy1haS1jYW4tc2ltdWxhdGUtYW55b25lcy12b2ljZS13aXRoLTMtc2Vjb25kcy1vZi1hdWRpby_SAYABaHR0cHM6Ly9hcnN0ZWNobmljYS5jb20vaW5mb3JtYXRpb24tdGVjaG5vbG9neS8yMDIzLzAxL21pY3Jvc29mdHMtbmV3LWFpLWNhbi1zaW11bGF0ZS1hbnlvbmVzLXZvaWNlLXdpdGgtMy1zZWNvbmRzLW9mLWF1ZGlvL2FtcC8?oc=5\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Microsoft&#039;s new AI can simulate anyone&#039;s voice with 3 seconds of audio - harchi90\" \/>\n<meta property=\"og:description\" content=\"enlarge \/ An AI-generated image of a person&#8217;s silhouette. Ars Technica On Thursday, Microsoft researchers announced a new text-to-speech AI model called VALL-E that 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 &hellip; Microsoft&#8217;s new AI can simulate anyone&#8217;s voice with 3 seconds of audio Read More &raquo;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/news.google.com\/__i\/rss\/rd\/articles\/CBMifGh0dHBzOi8vYXJzdGVjaG5pY2EuY29tL2luZm9ybWF0aW9uLXRlY2hub2xvZ3kvMjAyMy8wMS9taWNyb3NvZnRzLW5ldy1haS1jYW4tc2ltdWxhdGUtYW55b25lcy12b2ljZS13aXRoLTMtc2Vjb25kcy1vZi1hdWRpby_SAYABaHR0cHM6Ly9hcnN0ZWNobmljYS5jb20vaW5mb3JtYXRpb24tdGVjaG5vbG9neS8yMDIzLzAxL21pY3Jvc29mdHMtbmV3LWFpLWNhbi1zaW11bGF0ZS1hbnlvbmVzLXZvaWNlLXdpdGgtMy1zZWNvbmRzLW9mLWF1ZGlvL2FtcC8?oc=5\" \/>\n<meta property=\"og:site_name\" content=\"harchi90\" \/>\n<meta property=\"article:published_time\" content=\"2023-01-09T23:21:59+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cdn.arstechnica.net\/wp-content\/uploads\/2023\/01\/abstract_silhouette-760x380.jpg\" \/>\n<meta name=\"author\" content=\"islamlacoste58\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/cdn.arstechnica.net\/wp-content\/uploads\/2023\/01\/abstract_silhouette-760x380.jpg\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"islamlacoste58\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/harchi90.com\/microsofts-new-ai-can-simulate-anyones-voice-with-3-seconds-of-audio\/\",\"url\":\"https:\/\/news.google.com\/__i\/rss\/rd\/articles\/CBMifGh0dHBzOi8vYXJzdGVjaG5pY2EuY29tL2luZm9ybWF0aW9uLXRlY2hub2xvZ3kvMjAyMy8wMS9taWNyb3NvZnRzLW5ldy1haS1jYW4tc2ltdWxhdGUtYW55b25lcy12b2ljZS13aXRoLTMtc2Vjb25kcy1vZi1hdWRpby_SAYABaHR0cHM6Ly9hcnN0ZWNobmljYS5jb20vaW5mb3JtYXRpb24tdGVjaG5vbG9neS8yMDIzLzAxL21pY3Jvc29mdHMtbmV3LWFpLWNhbi1zaW11bGF0ZS1hbnlvbmVzLXZvaWNlLXdpdGgtMy1zZWNvbmRzLW9mLWF1ZGlvL2FtcC8?oc=5\",\"name\":\"Microsoft's new AI can simulate anyone's voice with 3 seconds of audio - harchi90\",\"isPartOf\":{\"@id\":\"https:\/\/harchi90.com\/#website\"},\"datePublished\":\"2023-01-09T23:21:59+00:00\",\"dateModified\":\"2023-01-09T23:21:59+00:00\",\"author\":{\"@id\":\"https:\/\/harchi90.com\/#\/schema\/person\/0689156e87fbe869f0e5efdeef200d5b\"},\"breadcrumb\":{\"@id\":\"https:\/\/news.google.com\/__i\/rss\/rd\/articles\/CBMifGh0dHBzOi8vYXJzdGVjaG5pY2EuY29tL2luZm9ybWF0aW9uLXRlY2hub2xvZ3kvMjAyMy8wMS9taWNyb3NvZnRzLW5ldy1haS1jYW4tc2ltdWxhdGUtYW55b25lcy12b2ljZS13aXRoLTMtc2Vjb25kcy1vZi1hdWRpby_SAYABaHR0cHM6Ly9hcnN0ZWNobmljYS5jb20vaW5mb3JtYXRpb24tdGVjaG5vbG9neS8yMDIzLzAxL21pY3Jvc29mdHMtbmV3LWFpLWNhbi1zaW11bGF0ZS1hbnlvbmVzLXZvaWNlLXdpdGgtMy1zZWNvbmRzLW9mLWF1ZGlvL2FtcC8?oc=5#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/news.google.com\/__i\/rss\/rd\/articles\/CBMifGh0dHBzOi8vYXJzdGVjaG5pY2EuY29tL2luZm9ybWF0aW9uLXRlY2hub2xvZ3kvMjAyMy8wMS9taWNyb3NvZnRzLW5ldy1haS1jYW4tc2ltdWxhdGUtYW55b25lcy12b2ljZS13aXRoLTMtc2Vjb25kcy1vZi1hdWRpby_SAYABaHR0cHM6Ly9hcnN0ZWNobmljYS5jb20vaW5mb3JtYXRpb24tdGVjaG5vbG9neS8yMDIzLzAxL21pY3Jvc29mdHMtbmV3LWFpLWNhbi1zaW11bGF0ZS1hbnlvbmVzLXZvaWNlLXdpdGgtMy1zZWNvbmRzLW9mLWF1ZGlvL2FtcC8?oc=5\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/news.google.com\/__i\/rss\/rd\/articles\/CBMifGh0dHBzOi8vYXJzdGVjaG5pY2EuY29tL2luZm9ybWF0aW9uLXRlY2hub2xvZ3kvMjAyMy8wMS9taWNyb3NvZnRzLW5ldy1haS1jYW4tc2ltdWxhdGUtYW55b25lcy12b2ljZS13aXRoLTMtc2Vjb25kcy1vZi1hdWRpby_SAYABaHR0cHM6Ly9hcnN0ZWNobmljYS5jb20vaW5mb3JtYXRpb24tdGVjaG5vbG9neS8yMDIzLzAxL21pY3Jvc29mdHMtbmV3LWFpLWNhbi1zaW11bGF0ZS1hbnlvbmVzLXZvaWNlLXdpdGgtMy1zZWNvbmRzLW9mLWF1ZGlvL2FtcC8?oc=5#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/harchi90.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Microsoft&#8217;s new AI can simulate anyone&#8217;s voice with 3 seconds of audio\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/harchi90.com\/#website\",\"url\":\"https:\/\/harchi90.com\/\",\"name\":\"harchi90\",\"description\":\"Just another WordPress site\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/harchi90.com\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/harchi90.com\/#\/schema\/person\/0689156e87fbe869f0e5efdeef200d5b\",\"name\":\"islamlacoste58\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/harchi90.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/5bf7491076e3822b8e0de7b1f9364d75?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/5bf7491076e3822b8e0de7b1f9364d75?s=96&d=mm&r=g\",\"caption\":\"islamlacoste58\"},\"sameAs\":[\"http:\/\/harchi90.com\"],\"url\":\"https:\/\/harchi90.com\/author\/islamlacoste58\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Microsoft's new AI can simulate anyone's voice with 3 seconds of audio - harchi90","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/news.google.com\/__i\/rss\/rd\/articles\/CBMifGh0dHBzOi8vYXJzdGVjaG5pY2EuY29tL2luZm9ybWF0aW9uLXRlY2hub2xvZ3kvMjAyMy8wMS9taWNyb3NvZnRzLW5ldy1haS1jYW4tc2ltdWxhdGUtYW55b25lcy12b2ljZS13aXRoLTMtc2Vjb25kcy1vZi1hdWRpby_SAYABaHR0cHM6Ly9hcnN0ZWNobmljYS5jb20vaW5mb3JtYXRpb24tdGVjaG5vbG9neS8yMDIzLzAxL21pY3Jvc29mdHMtbmV3LWFpLWNhbi1zaW11bGF0ZS1hbnlvbmVzLXZvaWNlLXdpdGgtMy1zZWNvbmRzLW9mLWF1ZGlvL2FtcC8?oc=5","og_locale":"en_US","og_type":"article","og_title":"Microsoft's new AI can simulate anyone's voice with 3 seconds of audio - harchi90","og_description":"enlarge \/ An AI-generated image of a person&#8217;s silhouette. Ars Technica On Thursday, Microsoft researchers announced a new text-to-speech AI model called VALL-E that 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 &hellip; Microsoft&#8217;s new AI can simulate anyone&#8217;s voice with 3 seconds of audio Read More &raquo;","og_url":"https:\/\/news.google.com\/__i\/rss\/rd\/articles\/CBMifGh0dHBzOi8vYXJzdGVjaG5pY2EuY29tL2luZm9ybWF0aW9uLXRlY2hub2xvZ3kvMjAyMy8wMS9taWNyb3NvZnRzLW5ldy1haS1jYW4tc2ltdWxhdGUtYW55b25lcy12b2ljZS13aXRoLTMtc2Vjb25kcy1vZi1hdWRpby_SAYABaHR0cHM6Ly9hcnN0ZWNobmljYS5jb20vaW5mb3JtYXRpb24tdGVjaG5vbG9neS8yMDIzLzAxL21pY3Jvc29mdHMtbmV3LWFpLWNhbi1zaW11bGF0ZS1hbnlvbmVzLXZvaWNlLXdpdGgtMy1zZWNvbmRzLW9mLWF1ZGlvL2FtcC8?oc=5","og_site_name":"harchi90","article_published_time":"2023-01-09T23:21:59+00:00","og_image":[{"url":"https:\/\/cdn.arstechnica.net\/wp-content\/uploads\/2023\/01\/abstract_silhouette-760x380.jpg"}],"author":"islamlacoste58","twitter_card":"summary_large_image","twitter_image":"https:\/\/cdn.arstechnica.net\/wp-content\/uploads\/2023\/01\/abstract_silhouette-760x380.jpg","twitter_misc":{"Written by":"islamlacoste58","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/harchi90.com\/microsofts-new-ai-can-simulate-anyones-voice-with-3-seconds-of-audio\/","url":"https:\/\/news.google.com\/__i\/rss\/rd\/articles\/CBMifGh0dHBzOi8vYXJzdGVjaG5pY2EuY29tL2luZm9ybWF0aW9uLXRlY2hub2xvZ3kvMjAyMy8wMS9taWNyb3NvZnRzLW5ldy1haS1jYW4tc2ltdWxhdGUtYW55b25lcy12b2ljZS13aXRoLTMtc2Vjb25kcy1vZi1hdWRpby_SAYABaHR0cHM6Ly9hcnN0ZWNobmljYS5jb20vaW5mb3JtYXRpb24tdGVjaG5vbG9neS8yMDIzLzAxL21pY3Jvc29mdHMtbmV3LWFpLWNhbi1zaW11bGF0ZS1hbnlvbmVzLXZvaWNlLXdpdGgtMy1zZWNvbmRzLW9mLWF1ZGlvL2FtcC8?oc=5","name":"Microsoft's new AI can simulate anyone's voice with 3 seconds of audio - harchi90","isPartOf":{"@id":"https:\/\/harchi90.com\/#website"},"datePublished":"2023-01-09T23:21:59+00:00","dateModified":"2023-01-09T23:21:59+00:00","author":{"@id":"https:\/\/harchi90.com\/#\/schema\/person\/0689156e87fbe869f0e5efdeef200d5b"},"breadcrumb":{"@id":"https:\/\/news.google.com\/__i\/rss\/rd\/articles\/CBMifGh0dHBzOi8vYXJzdGVjaG5pY2EuY29tL2luZm9ybWF0aW9uLXRlY2hub2xvZ3kvMjAyMy8wMS9taWNyb3NvZnRzLW5ldy1haS1jYW4tc2ltdWxhdGUtYW55b25lcy12b2ljZS13aXRoLTMtc2Vjb25kcy1vZi1hdWRpby_SAYABaHR0cHM6Ly9hcnN0ZWNobmljYS5jb20vaW5mb3JtYXRpb24tdGVjaG5vbG9neS8yMDIzLzAxL21pY3Jvc29mdHMtbmV3LWFpLWNhbi1zaW11bGF0ZS1hbnlvbmVzLXZvaWNlLXdpdGgtMy1zZWNvbmRzLW9mLWF1ZGlvL2FtcC8?oc=5#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/news.google.com\/__i\/rss\/rd\/articles\/CBMifGh0dHBzOi8vYXJzdGVjaG5pY2EuY29tL2luZm9ybWF0aW9uLXRlY2hub2xvZ3kvMjAyMy8wMS9taWNyb3NvZnRzLW5ldy1haS1jYW4tc2ltdWxhdGUtYW55b25lcy12b2ljZS13aXRoLTMtc2Vjb25kcy1vZi1hdWRpby_SAYABaHR0cHM6Ly9hcnN0ZWNobmljYS5jb20vaW5mb3JtYXRpb24tdGVjaG5vbG9neS8yMDIzLzAxL21pY3Jvc29mdHMtbmV3LWFpLWNhbi1zaW11bGF0ZS1hbnlvbmVzLXZvaWNlLXdpdGgtMy1zZWNvbmRzLW9mLWF1ZGlvL2FtcC8?oc=5"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/news.google.com\/__i\/rss\/rd\/articles\/CBMifGh0dHBzOi8vYXJzdGVjaG5pY2EuY29tL2luZm9ybWF0aW9uLXRlY2hub2xvZ3kvMjAyMy8wMS9taWNyb3NvZnRzLW5ldy1haS1jYW4tc2ltdWxhdGUtYW55b25lcy12b2ljZS13aXRoLTMtc2Vjb25kcy1vZi1hdWRpby_SAYABaHR0cHM6Ly9hcnN0ZWNobmljYS5jb20vaW5mb3JtYXRpb24tdGVjaG5vbG9neS8yMDIzLzAxL21pY3Jvc29mdHMtbmV3LWFpLWNhbi1zaW11bGF0ZS1hbnlvbmVzLXZvaWNlLXdpdGgtMy1zZWNvbmRzLW9mLWF1ZGlvL2FtcC8?oc=5#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/harchi90.com\/"},{"@type":"ListItem","position":2,"name":"Microsoft&#8217;s new AI can simulate anyone&#8217;s voice with 3 seconds of audio"}]},{"@type":"WebSite","@id":"https:\/\/harchi90.com\/#website","url":"https:\/\/harchi90.com\/","name":"harchi90","description":"Just another WordPress site","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/harchi90.com\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/harchi90.com\/#\/schema\/person\/0689156e87fbe869f0e5efdeef200d5b","name":"islamlacoste58","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/harchi90.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/5bf7491076e3822b8e0de7b1f9364d75?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/5bf7491076e3822b8e0de7b1f9364d75?s=96&d=mm&r=g","caption":"islamlacoste58"},"sameAs":["http:\/\/harchi90.com"],"url":"https:\/\/harchi90.com\/author\/islamlacoste58\/"}]}},"jetpack_featured_media_url":"","jetpack-related-posts":[{"id":183967,"url":"https:\/\/harchi90.com\/this-new-ai-can-simulate-your-voice-from-just-3-seconds-of-audio\/","url_meta":{"origin":182031,"position":0},"title":"This new AI can simulate your voice from just 3 seconds of audio","date":"January 11, 2023","format":false,"excerpt":"Microsoft's new language model Vall-E is reportedly able to imitate any voice using just a three-second sample recording. The recently released AI tool was tested on 60,000 hours of English speech data. Researchers said in a paper out of Cornell University that it could replicate the emotions and tone of\u2026","rel":"","context":"In &quot;Technology&quot;","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":182725,"url":"https:\/\/harchi90.com\/microsofts-vall-e-ai-can-mimic-any-voice-from-a-short-audio-sample\/","url_meta":{"origin":182031,"position":1},"title":"Microsoft&#8217;s VALL-E AI can mimic any voice from a short audio sample","date":"January 10, 2023","format":false,"excerpt":"Microsoft has shown off its latest research in text-to-speech AI with a model called VALL-E that can simulate someone's voice from just a three-second audio sample, Ars Technica has reported. The speech can not only match the timbre but also the emotional tone of the speaker, and even the acoustics\u2026","rel":"","context":"In &quot;Technology&quot;","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":182813,"url":"https:\/\/harchi90.com\/microsofts-new-ai-tool-can-mimic-voices-with-3-seconds-of-audio\/","url_meta":{"origin":182031,"position":2},"title":"Microsoft&#8217;s New AI Tool Can Mimic Voices With 3 Seconds of Audio","date":"January 10, 2023","format":false,"excerpt":"Despite how far advancements in AI video generation have come, it still requires quite a bit of source material, like headshots from various angles or video footage, for someone to create a convincing deepfaked version of your likeness. When it comes to faking your voice, that's a different story, as\u2026","rel":"","context":"In &quot;Technology&quot;","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":185568,"url":"https:\/\/harchi90.com\/after-chatgpt-and-dall-e-meet-vall-e-the-text-to-speech-ai-that-can-mimic-anyones-voice\/","url_meta":{"origin":182031,"position":3},"title":"After ChatGPT and DALL-E, meet VALL-E &#8211; the text-to-speech AI that can mimic anyone&#8217;s voice","date":"January 13, 2023","format":false,"excerpt":"Last year saw the emergence of artificial intelligence tools (AI) that can create images, artwork, or even video with a text prompt.There were also major steps forward in AI writingwith OpenAI's ChatGPT causing widespread excitement - and fear - about the future of writing.Now, just a few days into 2023,\u2026","rel":"","context":"In &quot;Technology&quot;","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":187786,"url":"https:\/\/harchi90.com\/microsoft-quietly-revealed-a-new-type-of-ai-it-may-quietly-petrify-you\/","url_meta":{"origin":182031,"position":4},"title":"Microsoft quietly revealed a new type of AI (it may quietly petrify you)","date":"January 16, 2023","format":false,"excerpt":"Getty ImagesIt's quite a privilege being one of the last, whole humans.more Technically Incorrect I'm conscious that in the tangible future, the artists formerly known as humans will be a touching hybrid of flesh and chips.Perhaps I shouldn't have been surprised, then, when Microsoft's researchers came along to slightly hasten\u2026","rel":"","context":"In &quot;Technology&quot;","img":{"alt_text":"Microsoft building","src":"https:\/\/i0.wp.com\/www.zdnet.com\/a\/img\/resize\/4e010fb0d3e6c4553f7935db43c98e3d941fe29a\/2022\/10\/27\/46f75d8a-8103-4613-855e-e9e3c1381ccd\/microsoft-getty.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]}],"fifu_image_url":"https:\/\/cdn.arstechnica.net\/wp-content\/uploads\/2023\/01\/abstract_silhouette-760x380.jpg","_links":{"self":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/posts\/182031"}],"collection":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/comments?post=182031"}],"version-history":[{"count":0,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/posts\/182031\/revisions"}],"wp:attachment":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/media?parent=182031"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/categories?post=182031"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/tags?post=182031"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}