{"id":356,"date":"2019-10-10T21:20:01","date_gmt":"2019-10-10T21:20:01","guid":{"rendered":"http:\/\/www.oxo.com.ar\/npv\/?page_id=356"},"modified":"2019-10-11T22:32:02","modified_gmt":"2019-10-11T22:32:02","slug":"oxo-lyra-a-i-microservices","status":"publish","type":"page","link":"http:\/\/www.oxo.com.ar\/npv\/oxo-lyra-a-i-microservices\/","title":{"rendered":"A.I MICRO SERVICES"},"content":{"rendered":"<h4><strong>OXO LYRA: DIALOGUE DETECTOR MICRO SERVICE BASED IN A.I\u00a0<\/strong><\/h4>\n<p><span style=\"font-weight: 400;\">The <a href=\"http:\/\/www.oxo.com.ar\/npv\/package-player-and-editor\/\">OxoPackage Player Editor\u00a0<\/a> counts with a micro service called Oxo Lyra,\u00a0developed using machine learning. OxoLyra detects dialogues and creates a perfectly-timed subtitle template that complies with Netflix\u2019s standards. These timed lines are empty, allowing linguists to focus only on transcription and translation tasks, even when working with large-scale projects. With this A.I approach and using GPU, Oxo Lyra takes only 40 seconds to analyze a 90 minute-long feature and to produce a DFXP file with accurate subtitle timing.<\/span><\/p>\n<p><iframe loading=\"lazy\" src=\"https:\/\/ott.oxobox.net\/UKnIYrw2\/player\/?\" width=\"640\" height=\"480\" frameborder=\"0\" allowfullscreen=\"allowfullscreen\"><\/iframe><\/p>\n<p><span style=\"font-weight: 400;\">Oxobox platforms extract the audio track from the proxy file and move the audio file to the Lyra environment where an inference algorithm analyzes it in and runs a process that looks for the sound of the human voice. The machine learning system of Lyra was trained to \u201chear\u201d human voice using thousands of segments belong to a hundred hours of series and film features hat was subtitled and QCed by skilled people and create lines of the subtitle empty of text.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Then, these lines are adjusted by a posts process under a set of restrictions and rules present in the <a href=\"https:\/\/partnerhelp.netflixstudios.com\/hc\/en-us\/articles\/215758617-Timed-Text-Style-Guide-General-Requirements\">Netflix Specs<\/a> Guide for Timed Text. This post-process is parametric in order to produce different results, depending on the kind of content( I.E: adult or kids content determines the reading speed and, musical may need a different length)<\/span><\/p>\n<p><span style=\"font-weight: 400;\">After 20 seconds Lyra delivers an SRT file for a 45 minutes episode that contains a very reliable subtitle that has the right quantity of lines located in the best audio position. Each line has the right length and complains all the <a href=\"https:\/\/partnerhelp.netflixstudios.com\/hc\/en-us\/articles\/215758617-Timed-Text-Style-Guide-General-Requirements\">Netflix specs<\/a> regarding duration and separation.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">In this way, it is possible to start to work with human operators with linguistic skills but technical.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">These operator has only to fill lines with text and eventually delete lines due to some false positives that the algorithm may produce.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>OXO LYRA: DIALOGUE DETECTOR MICRO SERVICE BASED IN A.I\u00a0 The OxoPackage Player Editor\u00a0 counts with a micro service called Oxo Lyra,\u00a0developed using machine learning. OxoLyra detects dialogues and creates a perfectly-timed subtitle template that complies with Netflix\u2019s standards. These timed lines are empty, allowing linguists to focus only on transcription and translation tasks, even when [&hellip;]<\/p>\n","protected":false},"author":5,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-356","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"http:\/\/www.oxo.com.ar\/npv\/wp-json\/wp\/v2\/pages\/356","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.oxo.com.ar\/npv\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/www.oxo.com.ar\/npv\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/www.oxo.com.ar\/npv\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"http:\/\/www.oxo.com.ar\/npv\/wp-json\/wp\/v2\/comments?post=356"}],"version-history":[{"count":6,"href":"http:\/\/www.oxo.com.ar\/npv\/wp-json\/wp\/v2\/pages\/356\/revisions"}],"predecessor-version":[{"id":389,"href":"http:\/\/www.oxo.com.ar\/npv\/wp-json\/wp\/v2\/pages\/356\/revisions\/389"}],"wp:attachment":[{"href":"http:\/\/www.oxo.com.ar\/npv\/wp-json\/wp\/v2\/media?parent=356"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.oxo.com.ar\/npv\/wp-json\/wp\/v2\/categories?post=356"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.oxo.com.ar\/npv\/wp-json\/wp\/v2\/tags?post=356"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}