{"id":102,"date":"2015-06-17T12:57:29","date_gmt":"2015-06-17T10:57:29","guid":{"rendered":"http:\/\/members.loria.fr\/template\/?page_id=102"},"modified":"2019-03-19T20:44:55","modified_gmt":"2019-03-19T18:44:55","slug":"equipe","status":"publish","type":"page","link":"https:\/\/members.loria.fr\/IIllina\/equipe\/","title":{"rendered":"Team"},"content":{"rendered":"<p>MULTISPEECH is a joint research team between the\u00a0<a href=\"http:\/\/www.univ-lorraine.fr\/\">Universit\u00e9 of Lorraine<\/a>, <a href=\"http:\/\/www.inria.fr\">Inria<\/a>, and <a href=\"http:\/\/www.cnrs.fr\">CNRS<\/a>. It is part of department D4 \u201cNatural language and knowledge processing\u201d of <a href=\"http:\/\/www.loria.fr\">LORIA<\/a>.<\/p>\n<p>Its research focuses on speech processing, with particular emphasis to <strong>multisource<\/strong> (source separation, robust speech recognition), <strong>multilingual<\/strong> (computer assisted language learning), and <strong>multimodal <\/strong>aspects (audiovisual synthesis).<\/p>\n<p>The research program is organized along the three following axes:<\/p>\n<ul>\n<li><strong>explicit speech modeling<\/strong>, which exploits the physical properties of speech,<\/li>\n<li><strong>statistical speech modeling<\/strong>, which relies on machine learning tools such as Bayesian models (HMM-GMM) and deep neural networks (DNN),<\/li>\n<li><strong>modeling of the uncertainties<\/strong> due to the strong variability of the speech signal and to model imperfections.<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>MULTISPEECH is a joint research team between the\u00a0<a href=\"http:\/\/www.univ-lorraine.fr\/\">Universit\u00e9 of Lorraine<\/a>, <a href=\"http:\/\/www.inria.fr\">Inria<\/a>, and <a href=\"http:\/\/www.cnrs.fr\">CNRS<\/a>. It is part of department D4 \u201cNatural language and knowledge processing\u201d of <a href=\"http:\/\/www.loria.fr\">LORIA<\/a>.<\/p>\n<p>Its research focuses on speech processing, with particular emphasis to multisource (source separation, robust speech recognition), multilingual (computer assisted language learning), and multimodal aspects (audiovisual synthesis).<\/p>\n<p>The research program is organized along the three following axes:<\/p>\n<ul>\n<li>explicit speech modeling, which exploits the physical properties of speech,<\/li>\n<li>statistical speech modeling, which relies on machine learning tools such as Bayesian models (HMM-GMM) and deep neural networks (DNN),<\/li>\n<\/ul>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-102","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/members.loria.fr\/IIllina\/wp-json\/wp\/v2\/pages\/102","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/members.loria.fr\/IIllina\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/members.loria.fr\/IIllina\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/members.loria.fr\/IIllina\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/members.loria.fr\/IIllina\/wp-json\/wp\/v2\/comments?post=102"}],"version-history":[{"count":21,"href":"https:\/\/members.loria.fr\/IIllina\/wp-json\/wp\/v2\/pages\/102\/revisions"}],"predecessor-version":[{"id":352,"href":"https:\/\/members.loria.fr\/IIllina\/wp-json\/wp\/v2\/pages\/102\/revisions\/352"}],"wp:attachment":[{"href":"https:\/\/members.loria.fr\/IIllina\/wp-json\/wp\/v2\/media?parent=102"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}