{"id":26695,"date":"2025-12-23T15:00:52","date_gmt":"2025-12-23T14:00:52","guid":{"rendered":"https:\/\/lium.univ-lemans.fr\/?p=26695"},"modified":"2026-04-13T09:48:32","modified_gmt":"2026-04-13T07:48:32","slug":"modelisation-extensible-de-langues-et-daccents","status":"publish","type":"post","link":"https:\/\/lium.univ-lemans.fr\/en\/modelisation-extensible-de-langues-et-daccents\/","title":{"rendered":"Mod\u00e9lisation Extensible de Langues et d’Accents"},"content":{"rendered":"

Seminar from Matthew Wiesner, associated researcher at LISN <\/h2>\n

 <\/p>\n

Date :<\/strong> 05\/01\/2026
\nTime :<\/strong> 10h30
\nPlace :<\/strong> IC2, Boardroom
\nSpeaker : <\/strong> Matthew Wiesner<\/a>
\n 
\n <\/p>\n

Modeling Accent and Language at Scale<\/strong><\/p>\n

 <\/p>\n

Abstract: <\/strong> State-of-the-art LID models work reliably for \u223c100 languages, but there are orders of magnitude more accents and dialects; annotating all of them is intractable. Furthermore, current LID models fail dramatically when applied to accented speech, and very few annotated accented data exist to support accented TTS.<\/p>\n

This talk explores these challenges and proposes a potential partial solution using massive amounts of diverse and widely available data collected from radio, with soft language labels in the form of geolocations. The talk then explores the link between robustness to accented speech and the capacity to more effectively model sequence-level data. Finally, these models and insights are shown to greatly improve LID on accented speech, and can be used to mine for accented speech to support scalable, controllable accented TTS.<\/p><\/div><\/div><\/div><\/div>

<\/div><\/div><\/div><\/div><\/div>
 <\/div>
 <\/div>
 <\/div><\/div><\/div>","protected":false},"excerpt":{"rendered":"

Seminar from Matthew Wiesner, associated researcher at LISN   Date : 05\/01\/2026 Time : 10h30 Place : IC2, Boardroom Speaker : Matthew Wiesner     Modeling Accent and Language at Scale   Abstract: State-of-the-art LID models work reliably for \u223c100 languages, but there are orders of magnitude more accents and dialects; annotating all of them […]<\/p>\n

READ MORE<\/span><\/i><\/span><\/a><\/p>\n","protected":false},"author":14,"featured_media":13238,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[46,43],"tags":[49],"acf":[],"_links":{"self":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts\/26695"}],"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=26695"}],"version-history":[{"count":5,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts\/26695\/revisions"}],"predecessor-version":[{"id":26858,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/posts\/26695\/revisions\/26858"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/media\/13238"}],"wp:attachment":[{"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/media?parent=26695"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/categories?post=26695"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lium.univ-lemans.fr\/en\/wp-json\/wp\/v2\/tags?post=26695"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}