{"id":74,"date":"2018-11-23T10:41:22","date_gmt":"2018-11-23T10:41:22","guid":{"rendered":"http:\/\/speechlabs.pl\/?page_id=74"},"modified":"2018-12-18T09:38:36","modified_gmt":"2018-12-18T09:38:36","slug":"tin","status":"publish","type":"page","link":"https:\/\/speechlabs.pl\/en\/our-offer\/tin\/","title":{"rendered":"TIN"},"content":{"rendered":"\t<p>\r\n\t\t<b>TIN is a system for fast multi-criterion text phrase search in larger audio and video databases. Full-text indexing is performed on recordings&#8217; transcripts obtained through speech recognition. It is a server-client solution for Windows  which exhibits high scalability with web client applications.<\/b>\r\n\t<\/p>\r\n\t<img decoding=\"async\" class=\"product-img\" src=\"\/wp-content\/uploads\/2018\/11\/tin_screen.jpg\" title=\"TIN\" \/>\r\n\t<p>\r\n\t\tTIN has been designed mainly for use by internal security agencies. It enables full-text search of recordings database required for operational and procedural activities. Large database search performed manually can be very time and resource consuming, and therefore expensive. Full-text indexing of the transcripts can speed-up that process, considerably decrease its costs and enable new ways of processing and use of the database.\r\n\t<\/p><br\/>\r\n\t<label>The <b>main applications<\/b> of the system is a text search of the following types of  databases:<\/label>\r\n\t<ul class=\"disc\">\r\n\t\t<li>emergency phone system recordings<\/li>\r\n\t\t<li>phone info line recordings<\/li>\r\n\t\t<li>operational recordings<\/li>\r\n\t<\/ul>\r\n\t<p>\r\n\t\t <b>Other applications<\/b> include text search of conference recordings, parliament sessions and court proceedings.\r\n\t<\/p><br\/>\r\n\t<p>\r\n\t\t TIN performs <b>automatic speech recognition<\/b> and <b>full-text indexing<\/b> of the obtained recordings&#8217; transcripts. It can <b>process<\/b> a large number of <b>recordings in parallel<\/b> thanks to its scalability. TIN exploits the original ASR engine adapted to process <b>recordings of various types<\/b>. Various engine settings dedicated to these types are defined which facilitates speech recognition optimization.\r\n\t<\/p><br\/>\r\n\t<p>\r\n\t\t TIN performs <b>text phrase search<\/b> in various modes, e.g. verbatim as specified by a user or including all grammar forms of the specified words. The search process can utilize standard <b>thesaurus<\/b> as well as synonym sets defined by the user. The latter feature allows one to adjust the search process to specific vocabulary used in the recordings.\r\n\t<\/p>\r\n\t<img decoding=\"async\" class=\"product-img\" src=\"\/wp-content\/uploads\/2018\/12\/arm_schemat_transkrypcja_mowa_tekst_EN.png\"  title=\"TIN\" \/>\r\n\t<label class=\"img-label\">TIN system scheme<\/label>\r\n\t<p>\r\n\t<label>System ensures <b>accountability<\/b> and <b>non-repudiation<\/b> through:<\/label>\r\n\t<ul class=\"disc\">\r\n\t\t<li>user authentication &#8211; TIN can be integrated with an external authentication service<\/li>\r\n\t\t<li>authorization &#8211; system administrator defines a set of operations each user can perform on various recording sets<\/li>\r\n\t\t<li>key user actions are logged<\/li>\r\n\t<\/ul>\r\n\t<label>TIN is a <b>server-client solution<\/b> with the following features:<\/label>\r\n\t<ul class=\"disc\">\r\n\t\t<li>a <b>web application<\/b> is used to access recordings and search results<\/li>\r\n\t\t<li><b>data<\/b> (recordings, their metadata and transcripts) can be <b>exported<\/b> and searched locally on the user&#8217;s machine (in case user does not have direct access to TIN)<\/li>\r\n\t\t<li>TIN does not require communication with any external service, i.e. service outside of the local network<\/li>\r\n\t<\/ul>\r\n\t<label>TIN encompasses the following components:<\/label>\r\n\t<ul class=\"disc\">\r\n\t\t<li><b>Recording Repository<\/b> offering reliable storage<\/li>\r\n\t\t<li><b>Database<\/b> for recordings metadata and transcripts as well as user data<\/li>\r\n\t\t<li><b>User authentication service<\/b> (optional)<\/li>\r\n\t\t<li><b>TIN module<\/b>  supervising speech recognition and text indexing<\/li>\r\n\t\t<li><b>ASR engine<\/b><\/li>\r\n\t\t<li><b>User applications<\/b> \r\n\t\t\t<ul class=\"circle\">\r\n\t\t\t\t<li>system management web application<\/li>\r\n\t\t\t\t<li>recordings management desktop application<\/li>\r\n\t\t\t\t<li>recordings search and browsing web application<\/li>\r\n\t\t\t<\/ul>\r\n\t\t<\/li>\r\n\t<\/ul>\r\n\t<\/p>\r\n\t<p>\r\n\t\tTIN is one of the results of <a href=\"https:\/\/speechlabs.pl\/en\/completed\/#arm1\">ARM-1<\/a> project. It was designed in close cooperation with internal security agencies. TIN is a server solution for Windows.\r\n\t<\/p>","protected":false},"excerpt":{"rendered":"TIN is a system for fast multi-criterion text phrase search in larger audio and video databases. Full-text indexing is performed on recordings&#8217; transcripts obtained through speech recognition. It is a server-client solution for Windows which exhibits high scalability with web client applications. TIN has been designed mainly for use by internal security agencies. It enables [&hellip;]","protected":false},"author":1,"featured_media":0,"parent":70,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_locale":"en_US","_original_post":"60","footnotes":""},"class_list":["post-74","page","type-page","status-publish","hentry","en-US"],"meta_box":{"parallax_image":{"width":150,"height":150,"file":"2018\/12\/IMG_2379.jpg","sizes":{"thumbnail":{"file":"IMG_2379-150x150.jpg","width":150,"height":150,"mime-type":"image\/jpeg","url":"https:\/\/speechlabs.pl\/wp-content\/uploads\/2018\/12\/IMG_2379-150x150.jpg"},"medium":{"file":"IMG_2379-300x200.jpg","width":300,"height":200,"mime-type":"image\/jpeg","url":"https:\/\/speechlabs.pl\/wp-content\/uploads\/2018\/12\/IMG_2379-300x200.jpg"},"medium_large":{"file":"IMG_2379-768x512.jpg","width":768,"height":512,"mime-type":"image\/jpeg","url":"https:\/\/speechlabs.pl\/wp-content\/uploads\/2018\/12\/IMG_2379-768x512.jpg"},"large":{"file":"IMG_2379-1024x682.jpg","width":1024,"height":682,"mime-type":"image\/jpeg","url":"https:\/\/speechlabs.pl\/wp-content\/uploads\/2018\/12\/IMG_2379-1024x682.jpg"}},"image_meta":{"aperture":"4","credit":"","camera":"Canon EOS 7D","caption":"","created_timestamp":"1455626461","copyright":"","focal_length":"8","iso":"100","shutter_speed":"0.3","title":"","orientation":"1","keywords":[]},"ID":"467","name":"IMG_2379.jpg","path":"\/home\/sftpusers\/speechlabs\/www\/wp-content\/uploads\/2018\/12\/IMG_2379.jpg","url":"https:\/\/speechlabs.pl\/wp-content\/uploads\/2018\/12\/IMG_2379-150x150.jpg","full_url":"https:\/\/speechlabs.pl\/wp-content\/uploads\/2018\/12\/IMG_2379.jpg","title":"IMG_2379","caption":"","description":"","alt":"","srcset":false},"parallax_position":"center center","hide_news":"0","extra_content":"","custom_title":"","custom_title_link":"","enable_slider":"0","slide":[{"_state":"collapsed"}]},"_links":{"self":[{"href":"https:\/\/speechlabs.pl\/wp-json\/wp\/v2\/pages\/74","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/speechlabs.pl\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/speechlabs.pl\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/speechlabs.pl\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/speechlabs.pl\/wp-json\/wp\/v2\/comments?post=74"}],"version-history":[{"count":9,"href":"https:\/\/speechlabs.pl\/wp-json\/wp\/v2\/pages\/74\/revisions"}],"predecessor-version":[{"id":717,"href":"https:\/\/speechlabs.pl\/wp-json\/wp\/v2\/pages\/74\/revisions\/717"}],"up":[{"embeddable":true,"href":"https:\/\/speechlabs.pl\/wp-json\/wp\/v2\/pages\/70"}],"wp:attachment":[{"href":"https:\/\/speechlabs.pl\/wp-json\/wp\/v2\/media?parent=74"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}