{"id":216,"date":"2016-06-28T00:12:44","date_gmt":"2016-06-28T00:12:44","guid":{"rendered":"http:\/\/uscictdialdev.wpenginepowered.com\/?page_id=216"},"modified":"2016-07-18T16:30:36","modified_gmt":"2016-07-18T16:30:36","slug":"otosense-kaldi","status":"publish","type":"page","link":"https:\/\/dialport.ict.usc.edu\/index.php\/otosense-kaldi\/","title":{"rendered":"Otosense-Kaldi"},"content":{"rendered":"<p><strong><a href=\"http:\/\/kaldi-asr.org\/doc\/about.html\">Home<\/a>\u00a0 \u00a0<a href=\"http:\/\/kaldi-asr.org\/doc\/install.html\">Download<\/a>\u00a0 \u00a0<a href=\"http:\/\/kaldi-asr.org\/doc\/tutorial.html\">Tutorial<\/a>\u00a0 \u00a0<\/strong><\/p>\n<p>Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers. For more detailed history and list of contributors see <a class=\"el\" href=\"http:\/\/kaldi-asr.org\/doc\/history.html\">History of the Kaldi project<\/a>.<\/p>\n<p>&nbsp;<\/p>\n<h4>Kaldi&#8217;s versus other toolkits<\/h4>\n<p>Kaldi is similar in aims and scope to HTK. The goal is to have modern and flexible code, written in C++, that is easy to modify and extend. Important features include:<\/p>\n<ul>\n<li>Code-level integration with Finite State Transducers (FSTs)\n<ul>\n<li>We compile against the OpenFst toolkit (using it as a library).<\/li>\n<\/ul>\n<\/li>\n<li>Extensive linear algebra support\n<ul>\n<li>We include a <a class=\"el\" href=\"http:\/\/kaldi-asr.org\/doc\/matrix.html\">matrix library<\/a> that wraps standard BLAS and LAPACK routines.<\/li>\n<\/ul>\n<\/li>\n<li>Extensible design\n<ul>\n<li>As far as possible, we provide our algorithms in the most generic form possible. For instance, our decoders are templated on an object that provides a score indexed by a (frame, fst-input-symbol) tuple. This means the decoder could work from any suitable source of scores, such as a neural net.<\/li>\n<\/ul>\n<\/li>\n<li>Open license\n<ul>\n<li>The code is licensed under Apache 2.0, which is one of the least restrictive licenses available.<\/li>\n<\/ul>\n<\/li>\n<li>Complete recipes\n<ul>\n<li>Our goal is to make available complete recipes for building speech recognition systems, that work from widely available databases such as those provided by the Linguistic Data Consortium (LDC).<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Home\u00a0 \u00a0Download\u00a0 \u00a0Tutorial\u00a0 \u00a0 Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers. For more detailed history and list of contributors see History of the Kaldi project. &nbsp; Kaldi&#8217;s versus other toolkits Kaldi is similar in aims and [&hellip;]<\/p>\n","protected":false},"author":19,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-216","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/pages\/216","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/users\/19"}],"replies":[{"embeddable":true,"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/comments?post=216"}],"version-history":[{"count":0,"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/pages\/216\/revisions"}],"wp:attachment":[{"href":"https:\/\/dialport.ict.usc.edu\/index.php\/wp-json\/wp\/v2\/media?parent=216"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}