Odyssey 2010: The Speaker and Language Recognition Workshop

Brno, Czech Republic
28 June 1 July 2010

Multiple Background Models for Speaker Verification

Wei-Qiang Zhang, Yuxiang Shan, Jia Liu (1)

(1) Tsinghua University

In Gaussian mixture model - universal background model (GMM-UBM) speaker verification system, UBM training is the first and the most important stage. However, few investigations have been carried out on how to select suitable training data. In this paper, a VTL-based criterion for UBM training data selection is investigated and a multiple background model (MBM) system is proposed. Experimental results on NIST SRE06 evaluation show that the presented method decreases the equal error rate (EER) of about 8% relatively when compared with the baseline.

Full Paper (PDF)

Bibliographic reference.  Zhang, Wei-Qiang / Shan, Yuxiang / Liu, Jia (2010): "Multiple Background Models for Speaker Verification", In Odyssey-2010, paper 009.