{"id":288596,"date":"2026-07-12T10:04:00","date_gmt":"2026-07-12T14:04:00","guid":{"rendered":"https:\/\/news-you-need.com\/index.php\/2026\/07\/12\/speech-privacy-hackaday\/"},"modified":"2026-07-12T10:35:06","modified_gmt":"2026-07-12T14:35:06","slug":"speech-privacy-hackaday","status":"publish","type":"post","link":"https:\/\/news-you-need.com\/index.php\/2026\/07\/12\/speech-privacy-hackaday\/","title":{"rendered":"Speech Privacy | Hackaday"},"content":{"rendered":"<p><a href=\"https:\/\/hackaday.com\/tag\/speech-privacy\/\">Speech Privacy | Hackaday<\/a><\/p>\n<p><a href=\"https:\/\/hackaday.com\/tag\/speech-privacy\/\">https:\/\/hackaday.com\/tag\/speech-privacy\/<\/a><\/p>\n<p>Publish Date: <a href=\"publish_date]\">2026-07-12 10:04:00<\/a><\/p>\n<p>Source Domain: <a href=\"hackaday.com\">hackaday.com<\/a><\/p>\n<p>Speaking is much faster than typing, and while it\u2019s an increasingly convenient way to interact with computers, it\u2019s hardly private. Providing speech privacy in a way we haven\u2019t seen before is this prototype tongue-reading system that uses machine learning and ultrasound to read tongue movements and turn them into decoded speech. Not only can a user speak without emitting a sound, since it doesn\u2019t read sound waves it\u2019s completely immune to noisy environments.<\/p>\n<p><img fetchpriority=\"high\" decoding=\"async\" data-attachment-id=\"1124513\" src=\"https:\/\/hackaday.com\/2026\/07\/12\/speak-silently-with-an-ultrasound-probe\/silent-speech-tongue\/\" data-orig-file=\"https:\/\/hackaday.com\/wp-content\/uploads\/2026\/07\/silent-speech-tongue.png\" data-orig-size=\"449,449\" data-comments-opened=\"1\" data-image-meta=\"{\"aperture\":\"0\",\"credit\":\"\",\"camera\":\"\",\"caption\":\"\",\"created_timestamp\":\"0\",\"copyright\":\"\",\"focal_length\":\"0\",\"iso\":\"0\",\"shutter_speed\":\"0\",\"title\":\"\",\"orientation\":\"0\",\"alt\":\"\"}\" data-image-title=\"silent speech tongue\" data-image-description=\"\" data-image-caption=\"\" data-large-file=\"https:\/\/hackaday.com\/wp-content\/uploads\/2026\/07\/silent-speech-tongue.png?w=449\" class=\"wp-image-1124513 size-medium\" alt=\"\" width=\"400\" height=\"400\" srcset=\"https:\/\/hackaday.com\/wp-content\/uploads\/2026\/07\/silent-speech-tongue.png 449w, https:\/\/hackaday.com\/wp-content\/uploads\/2026\/07\/silent-speech-tongue.png?resize=250,250 250w, https:\/\/hackaday.com\/wp-content\/uploads\/2026\/07\/silent-speech-tongue.png?resize=400,400 400w\" sizes=\"(max-width: 400px) 100vw, 400px\"\/>Tongues are a far richer source of speech data than reading lip and mouth movements.<\/p>\n<p>It turns out that tongue movements are a very rich source of information about speech, and an ultrasound probe under the chin takes very clear video of a tongue. With a dataset consisting of only around 50 hours of training data, the system has a 15.6% error rate and generalizes across different speakers (as long as they speak with similar accents).<\/p>\n<p>That error rate may seem high at first glance, but keep in mind this is for a prototype system built in a month around a relatively small training dataset. All indications are that better results are just a matter of better training.<\/p>\n<p>Probably the biggest drawback at the moment is the size of the ultrasound probe and the way it must be held under one\u2019s chin like a contact microphone, but at the moment the probe is an off-the-shelf model that is hardly optimized for either size, weight, or wearability. If the system seems promising enough, a probe resembling an adhesive patch might even be possible.<\/p>\n<p>It\u2019s certainly a different approach from others we\u2019ve seen in the past, including whispering while inhaling and reading lip and mouth movements.<\/p>\n<p><a href=\"https:\/\/hackaday.com\/tag\/speech-privacy\/\">Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Speech Privacy | Hackaday https:\/\/hackaday.com\/tag\/speech-privacy\/ Publish Date: 2026-07-12 10:04:00 Source Domain: hackaday.com Speaking is much&#8230;<\/p>\n","protected":false},"author":1,"featured_media":288597,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/s0.wp.com\/_si\/?t=eyJpbWciOiJodHRwczpcL1wvaGFja2FkYXkuY29tXC93cC1jb250ZW50XC91cGxvYWRzXC8yMDIwXC8wN1wvaGFja2FkYXktbG9nby13aXRoLXRleHQtb3BlbmdyYXBoLWRlZmF1bHQtaW1hZ2UuanBnIiwidHh0IjoiSGFja2FkYXkiLCJ0ZW1wbGF0ZSI6ImhpZ2h3YXkiLCJmb250IjoiIiwiYmxvZ19pZCI6MTU2NjcwMTc3fQ.kVPxWrsIQyGdD1cPoxYvzP1mD56qtpkNpW1nAFiZiIgMQ","fifu_image_alt":"","footnotes":""},"categories":[16],"tags":[],"class_list":["post-288596","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-privacy"],"_links":{"self":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/288596"}],"collection":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/comments?post=288596"}],"version-history":[{"count":1,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/288596\/revisions"}],"predecessor-version":[{"id":288598,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/288596\/revisions\/288598"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/288597"}],"wp:attachment":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=288596"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=288596"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=288596"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}