{"id":24277,"date":"2019-12-09T15:15:17","date_gmt":"2019-12-09T14:15:17","guid":{"rendered":"https:\/\/lium.univ-lemans.fr\/?p=24277"},"modified":"2019-12-10T10:39:28","modified_gmt":"2019-12-10T09:39:28","slug":"kevin-vythelingum","status":"publish","type":"post","link":"https:\/\/lium.univ-lemans.fr\/en\/kevin-vythelingum\/","title":{"rendered":"Kevin Vythelingum"},"content":{"rendered":"<div class=\"panel-grid\" id=\"pg-24277-0\" ><div class=\"panel-grid-core\"><div class=\"panel-grid-cell\" id=\"pgc-24277-0-0\" ><div class=\"panel-widget-style\" ><h2 style=\"text-align: justify;\"><span style=\"color: #e5442d;\">PhD defence,  Kevin Vythelingum <\/span><\/h2>\n<p><b>Date : <\/b>10\/12\/2019<br \/>\n<b>Heure : <\/b> 13h30<br \/>\n<b>Lieu : <\/b>Board room, IC2 building, LIUM, Le Mans Universit\u00e9<\/p>\n<p><span style=\"font-size: 18pt;\"><strong style=\"color: #e5442d;\">Title : <\/strong>Rapid, efficient and joint construction of speech recognition and synthesis systems for new languages<\/span><\/p>\n<p><span style=\"color: #e5442d;\"><strong><span style=\"font-size: 14pt;\">Jury members :<\/span><br \/>\n<\/strong><\/span><strong><span style=\"font-size: 12pt;\">Reviewers:<\/span><br \/>\n<\/strong>&#8211; Martine ADDA-DECKER (LPP, Universite\u0301 Paris 3 Sorbonne)<br \/>\n&#8211; Denis JOUVET (LORIA, INRIA Nancy)<br \/>\n<strong><span style=\"font-size: 12pt;\">Examiners: <\/span><\/strong><span style=\"font-size: 12pt;\"><br \/>\n&#8211; Sylvain MEIGNER (LIUM, Le Mans Universite\u0301)<\/span><br \/>\n<span style=\"font-size: 12pt;\"> &#8211; Jean-Franc\u0327ois BONASTRE (LIA, Universite\u0301 d\u2019Avignon)<br \/>\n<span style=\"font-size: 12pt;\"> &#8211; Damien LOLIVE (IRISA, Enssat Lannion)<br \/>\n<\/span><strong>Supervisor:<\/strong>  M.  Yannick Est\u00e8ve (LIA, Universite\u0301 d\u2019Avignon)<br \/>\n<strong>Co-supervisors:<\/strong><span style=\"font-size: 12pt;\"> :<br \/>\n&#8211; Olivier ROSEC (Voxygen)<\/span><br \/>\n<span style=\"font-size: 12pt;\"> &#8211; Anthony LARCHER (LIUM, Le Mans Universite\u0301)<\/p>\n<p><span style=\"color: #e5442d;\"><strong><span style=\"font-size: 14pt;\">Abstract :<br \/>\n<\/span> <\/strong><\/span><\/p>\n<p style=\"text-align: justify;\" align=\"justify\">We study in this thesis the joint construction of speech recognition and synthesis systems for new languages, with the goals of accuracy and quick development. The rapid development of voice technologies for new languages is driving scientific ambitions and is now considered strategic by industial players. However, language development research is led by a few research centers, each working on a limited number of languages. However, these technologies share many common points. Our study focuses on building and sharing tools between systems for creating lexicons, learning phonetic rules and taking advantage of imperfect data.<br \/>\nOur contributions focus on the selection of relevant data for learning acoustic models, the joint development of phonetizers and pronunciation lexicons for speech recognition and synthesis, and the use of neural models for phonetic transcription from text and speech signal. In addition, we present an approach for automatic detection of phonetic transcript errors in annotated speech signal databases. This study has shown that it is possible to significantly reduce the quantity of data annotation useful for the development of new text-to-speech systems. It naturally helps to reduce data collection time in the process of new systems creation. Finally, we study an application case by jointly building a system for recognizing and synthesizing speech for a new language.<\/p>\n<p style=\"text-align: justify;\" align=\"justify\"><strong><span style=\"color: #e5442d; font-size: 14pt;\">Keywords :<\/span><br \/>\n<\/strong>Automatic speech recognition, Text-to-speech synthesis, Phonemic transcription, Automatic error detection, New languages development, Imperfect data exploitation<\/p><\/div><\/div><\/div><\/div><div class=\"panel-grid\" id=\"pg-24277-1\" ><div class=\"panel-grid-core\"><div class=\"panel-grid-cell\" id=\"pgc-24277-1-0\" >&nbsp;<\/div><\/div><\/div>","protected":false},"excerpt":{"rendered":"<p>PhD defence, Kevin Vythelingum Date : 10\/12\/2019 Heure : 13h30 Lieu : Board room, IC2 building, LIUM, Le Mans Universit\u00e9 Title : Rapid, efficient and joint construction of speech recognition and synthesis systems for new languages Jury members : Reviewers: &#8211; Martine ADDA-DECKER (LPP, Universite\u0301 Paris 3 Sorbonne) &#8211; Denis JOUVET (LORIA, INRIA Nancy) Examiners: [&hellip;]<\/p>\n<p class=\"more-link style2\"><a href=\"https:\/\/lium.univ-lemans.fr\/en\/kevin-vythelingum\/\"  class=\"themebutton\"><span class=\"more-text\">READ MORE<\/span><span class=\"more-icon\"><i class=\"fa fa-angle-right fa-lg\"><\/i><\/span><\/a><\/p>\n","protected":false},"author":14,"featured_media":13241,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[6],"tags":[49],"acf":[],"_links":{"self":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts\/24277"}],"collection":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/users\/14"}],"replies":[{"embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/comments?post=24277"}],"version-history":[{"count":0,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts\/24277\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/media\/13241"}],"wp:attachment":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/media?parent=24277"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/categories?post=24277"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/tags?post=24277"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}