On the use of GSV-SVM for Speaker Diarization and Tracking

Abstract : In this paper, we present the use of Gaussian Supervectors with Support Vector Machines classifiers (GSV-SVM) in an acoustic speaker diarization and a speaker tracking system, compared with a standard Gaussian Mixture Model system based on adapted Universal Background Models (GMM-UBM). GSV-SVM systems (which share the adaptation step with the GMM-UBM systems) are observed to have comparable performances: for acoustic speaker diarization, the GMM-UBM system out-performs the GSV-SVM system on ESTER2 data but the latter system works better in the speaker tracking system. In particular , the linear combination of two systems at the score level outperforms each individual system.
Document type :
Conference papers
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

Contributor : Claude Barras <>
Submitted on : Tuesday, January 23, 2018 - 5:29:48 PM
Last modification on : Saturday, May 4, 2019 - 1:21:05 AM
Long-term archiving on : Thursday, May 24, 2018 - 9:26:38 AM


Publisher files allowed on an open archive


  • HAL Id : hal-01690274, version 1



Viet Le, Claude Barras, Marc Ferràs. On the use of GSV-SVM for Speaker Diarization and Tracking. Odyssey 2010: The Speaker and Language Recognition Workshop, Jun 2010, Brno, Czech Republic. ⟨hal-01690274⟩



Record views


Files downloads