{"id":336614,"date":"2017-03-24T01:40:50","date_gmt":"2017-03-23T17:40:50","guid":{"rendered":"http:\/\/techcrunch.com\/?p=1468187"},"modified":"2017-03-24T01:40:50","modified_gmt":"2017-03-23T17:40:50","slug":"youtubes-automatic-captioning-system-can-now-describe-sound-effects","status":"publish","type":"post","link":"https:\/\/people.utm.my\/asmawisham\/youtubes-automatic-captioning-system-can-now-describe-sound-effects\/","title":{"rendered":"YouTube\u2019s automatic captioning system can now describe sound effects"},"content":{"rendered":"<p><img decoding=\"async\" src=\"https:\/\/tctechcrunch2011.files.wordpress.com\/2016\/06\/youtube-logo.jpg?w=738\" class=\"\"\/><\/p>\n<p>YouTube has <a target=\"_blank\" href=\"https:\/\/googleblog.blogspot.com\/2009\/11\/automatic-captions-in-youtube.html\">long<\/a> had an automatic captioning system that, thanks to\u00a0Google\u2019s machine learning advances in recent years, has gotten pretty good at automatically transcribing spoken words in a video. As the company <a target=\"_blank\" href=\"https:\/\/research.googleblog.com\/2017\/03\/adding-sound-effect-information-to.html\">announced<\/a> today, its technology is now able to take this a step further by also captioning some of the ambient sounds like [LAUGHTER], [APPLAUSE] and [MUSIC].<\/p>\n<p>For now, the automatic effects captioning is\u00a0actually restricted to those exactly these three sounds. The reason for this, Google says, is due to the fact that these are also exactly the sounds that most video producers manually caption right now.<\/p>\n<p>\u201cWhile the sound space is obviously far richer and provides even more contextually relevant information than these three classes, the semantic information conveyed by these sound effects in the caption track is relatively unambiguous, as opposed to sounds like [RING] which raises the question of \u201cwhat was it that rang \u2013 a bell, an alarm, a phone?,\u201d Google engineer Sourish Chaudhuri explains in today\u2019s announcement.<\/p>\n<p>Now that Google has the systems in place to caption those sounds, though, it should relatively easy to also caption other sounds as well.<\/p>\n<p>In the backend, YouTube\u2019s\u00a0sound captioning system is based on a Deep Neural Network model\u00a0the team trained on a set of <a target=\"_blank\" href=\"http:\/\/dl.acm.org\/citation.cfm?id=2964310\">weakly labeled data<\/a>. Whenever a new video is now uploaded to YouTube, the\u00a0new system runs and tries to identify these sounds.\u00a0For those of you who want to know more about how the team achieved this (and how it used a modified <a target=\"_blank\" href=\"https:\/\/en.wikipedia.org\/wiki\/Viterbi_algorithm\">Viterbi algorithm<\/a>), Google\u2019s <a target=\"_blank\" href=\"https:\/\/research.googleblog.com\/2017\/03\/adding-sound-effect-information-to.html\">own blog<\/a> post\u00a0provides more details.<\/p>\n<p><a target=\"_blank\" href=\"https:\/\/tctechcrunch2011.files.wordpress.com\/2017\/03\/image00-2.png\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-1468203\" src=\"https:\/\/tctechcrunch2011.files.wordpress.com\/2017\/03\/image00-2.png?w=1024&#038;h=235\" alt=\"\" width=\"1024\" height=\"235\" srcset=\"https:\/\/tctechcrunch2011.files.wordpress.com\/2017\/03\/image00-2.png?w=1024&#038;h=235 1024w, https:\/\/tctechcrunch2011.files.wordpress.com\/2017\/03\/image00-2.png?w=150&#038;h=34 150w, https:\/\/tctechcrunch2011.files.wordpress.com\/2017\/03\/image00-2.png?w=300&#038;h=69 300w, https:\/\/tctechcrunch2011.files.wordpress.com\/2017\/03\/image00-2.png?w=768&#038;h=177 768w, https:\/\/tctechcrunch2011.files.wordpress.com\/2017\/03\/image00-2.png?w=680&#038;h=156 680w, https:\/\/tctechcrunch2011.files.wordpress.com\/2017\/03\/image00-2.png 1514w\" sizes=\"(max-width: 1024px) 100vw, 1024px\"\/><\/a><\/p>\n<p><small>Featured Image: <a target=\"_blank\" href=\"http:\/\/www.gettyimages.com\/license\/157547099\">ERIC PIERMONT<\/a>\/Getty Images<\/small><\/p>\n","protected":false},"excerpt":{"rendered":"<p><img loading=\"lazy\" decoding=\"async\" width=\"680\" height=\"452\" src=\"https:\/\/tctechcrunch2011.files.wordpress.com\/2016\/06\/youtube-logo.jpg?w=680\" class=\"attachment-large size-large wp-post-image\" alt=\"\" srcset=\"https:\/\/tctechcrunch2011.files.wordpress.com\/2016\/06\/youtube-logo.jpg?w=680 680w, https:\/\/tctechcrunch2011.files.wordpress.com\/2016\/06\/youtube-logo.jpg?w=150 150w, https:\/\/tctechcrunch2011.files.wordpress.com\/2016\/06\/youtube-logo.jpg?w=300 300w, https:\/\/tctechcrunch2011.files.wordpress.com\/2016\/06\/youtube-logo.jpg?w=768 768w, https:\/\/tctechcrunch2011.files.wordpress.com\/2016\/06\/youtube-logo.jpg 1024w\" sizes=\"(max-width: 680px) 100vw, 680px\" \/>&nbsp;YouTube has long had an automatic captioning system that, thanks to\u00a0Google&#8217;s machine learning advances in recent years, has gotten pretty good at automatically transcribing spoken words in a video. As the company announced today, its technology is now able to take this a step further by also captioning some of the ambient sounds like [LAUGHTER], [APPLAUSE] and [MUSIC].<br \/>\nFor now, the&#8230; <a href=\"https:\/\/techcrunch.com\/2017\/03\/23\/youtubes-automatic-captioning-system-can-now-describe-sound-effects\/?ncid=rss\">Read More<\/a><\/p>\n<div class=\"feedflare\">\n<a href=\"http:\/\/feeds.feedburner.com\/~ff\/Techcrunch?a=mOsUycybAF0:b3Y3h2BJPfc:2mJPEYqXBVI\"><img decoding=\"async\" src=\"http:\/\/feeds.feedburner.com\/~ff\/Techcrunch?d=2mJPEYqXBVI\" border=\"0\"><\/img><\/a> <a href=\"http:\/\/feeds.feedburner.com\/~ff\/Techcrunch?a=mOsUycybAF0:b3Y3h2BJPfc:7Q72WNTAKBA\"><img decoding=\"async\" src=\"http:\/\/feeds.feedburner.com\/~ff\/Techcrunch?d=7Q72WNTAKBA\" border=\"0\"><\/img><\/a> <a href=\"http:\/\/feeds.feedburner.com\/~ff\/Techcrunch?a=mOsUycybAF0:b3Y3h2BJPfc:yIl2AUoC8zA\"><img decoding=\"async\" src=\"http:\/\/feeds.feedburner.com\/~ff\/Techcrunch?d=yIl2AUoC8zA\" border=\"0\"><\/img><\/a> <a href=\"http:\/\/feeds.feedburner.com\/~ff\/Techcrunch?a=mOsUycybAF0:b3Y3h2BJPfc:-BTjWOF_DHI\"><img decoding=\"async\" src=\"http:\/\/feeds.feedburner.com\/~ff\/Techcrunch?i=mOsUycybAF0:b3Y3h2BJPfc:-BTjWOF_DHI\" border=\"0\"><\/img><\/a> <a href=\"http:\/\/feeds.feedburner.com\/~ff\/Techcrunch?a=mOsUycybAF0:b3Y3h2BJPfc:D7DqB2pKExk\"><img decoding=\"async\" src=\"http:\/\/feeds.feedburner.com\/~ff\/Techcrunch?i=mOsUycybAF0:b3Y3h2BJPfc:D7DqB2pKExk\" border=\"0\"><\/img><\/a> <a href=\"http:\/\/feeds.feedburner.com\/~ff\/Techcrunch?a=mOsUycybAF0:b3Y3h2BJPfc:qj6IDK7rITs\"><img decoding=\"async\" src=\"http:\/\/feeds.feedburner.com\/~ff\/Techcrunch?d=qj6IDK7rITs\" border=\"0\"><\/img><\/a>\n<\/div>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"http:\/\/feeds.feedburner.com\/~r\/Techcrunch\/~4\/mOsUycybAF0\" height=\"1\" width=\"1\" alt=\"\"\/> <\/p>\n","protected":false},"author":5817,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_et_pb_use_builder":"","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[25],"tags":[59,66,26],"class_list":["post-336614","post","type-post","status-publish","format-standard","hentry","category-technology","tag-media","tag-techcrunch","tag-technology"],"_links":{"self":[{"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/posts\/336614","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/users\/5817"}],"replies":[{"embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/comments?post=336614"}],"version-history":[{"count":0,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/posts\/336614\/revisions"}],"wp:attachment":[{"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/media?parent=336614"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/categories?post=336614"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/tags?post=336614"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}