http://cslt.org/mediawiki/index.php?action=history&feed=atom&title=Speaker_Technology_Group 2026-04-15T03:32:29Z 本wiki的该页面的版本历史 MediaWiki 1.23.3 http://cslt.org/mediawiki/index.php?title=Speaker_Technology_Group&diff=11633&oldid=prev 2014-09-30T08:21:05Z

<p>以“== &#039;&#039;&#039;Welcome to Speaker Recognition team in CSLT, RIIT, Tsinghua University.&#039;&#039;&#039;== Research focus: &#039;&#039;&#039;1. Robust speaker recognition&#039;&#039;&#039; We are interested in VPR ap...”为内容创建页面</p> <p><b>新页面</b></p><div>== '''Welcome to Speaker Recognition team in CSLT, RIIT, Tsinghua University.'''==<br /> <br /> Research focus:<br /> <br /> '''1. Robust speaker recognition'''<br /> <br /> We are interested in VPR approaches in adverse circumstances, including high noise, cross channel, truncated speech, emotional speech, aged speech.<br /> <br /> <br /> '''2. Short utterance speaker recognition'''<br /> <br /> People are reluctant to speak too much in VPR, but short utterances are highly challenging. We are interested in approaches particularly to speaker verification with speech signals as short as 1-5 seconds. <br /> <br /> <br /> '''3. Multi-lingual speaker recognition'''<br /> <br /> How to use multiple language data can be used collaboratively in SID is an open question, particularly, using the data of a dominant language to boost the performance for low-resource languages is highly interesting. <br /> <br /> <br /> <br /> ----<br /> <br /> <br /> [[SID-people|People]]<br /> <br /> [[SID-projects|Porjects]]<br /> <br /> [[SID-weekly-status|Weekly progress]]</div>

Cslt