https://www.hlt.inesc-id.pt/wiki/index.php?action=history&feed=atom&title=Speaker_and_Content_Identification 2026-05-17T21:42:24Z Revision history for this page on the wiki MediaWiki 1.41.0 https://www.hlt.inesc-id.pt/wiki/index.php?title=Speaker_and_Content_Identification&diff=6648&oldid=prev 2012-04-11T09:37:44Z

<p>Created page with &quot;__NOTOC__ {{speakerLargeBio| |name=Xavier Anguera |image=xavier.png |email=xanguera@tid.es |www=http://www.xavieranguera.com/ |bio=Xavier Anguera Miro: Ing. [MS] 2001 by UPC (Bar...&quot;</p> <p><b>New page</b></p><div>__NOTOC__<br /> {{speakerLargeBio|<br /> |name=Xavier Anguera<br /> |image=xavier.png<br /> |email=xanguera@tid.es<br /> |www=http://www.xavieranguera.com/<br /> |bio=Xavier Anguera Miro: Ing. [MS] 2001 by UPC (Barcelona, Spain), [MS] 2001 European Masters in Language and Speech, Dr. [PhD] 2006 UPC University, with a thesis on speaker diarization for multi-microphone meeting recordings. From 2001 to 2003 he worked for Panasonic Speech Technology Lab in Santa Barbara, CA. From 2004 to 2006 he was a visiting researcher at the International Computer Science Institute (ICSI) in Berkeley, CA. Since 2007 he is a research scientist at Telefonica Research in Barcelona. His research interests cover speech processing (both speaker and content-based) and multimodal multimedia processing.}}<br /> <br /> == Date ==<br /> <br /> * 15:00, Friday, April 13&lt;sup&gt;th&lt;/sup&gt;, 2012<br /> * Room 336<br /> <br /> == Speaker ==<br /> <br /> * Xavier Anguera, Telefonica Research<br /> <br /> == Abstract ==<br /> <br /> In this talk I will cover two of the topics I have been recently working on. On the one hand, with regard to speaker identification, I will introduce the use of binary fingerprints to model the voice of a speaker. Based on the projection of standard acoustic vectors into a special GMM model (representing the speaker acoustic space), high-dimensional binary vectors, which have been proven successful in identifying speakers for speaker verification and diarization tasks, are obtained. <br /> On the other hand, I will talk about current developments in pattern matching approaches that allow for the development of content-centric applications when little or no training data is available for a particular language. In particular, I will describe a query-by-example system I presented to Mediaeval 2011 evaluation, which uses a novel feature extraction front-end I further described in a paper at ICASSP 2012.<br /> <br /> <br /> <br /> '''Note:''' This seminar will be held in English.<br /> <br /> [[category:Seminars]]<br /> [[category:Seminars_2012]]</div>

Acbm