14thAnnual Conference of the International Speech Communication Association

Lyon, France
August 25-29, 2013

Sequential Model Adaptation for Speaker Verification

Jun Wang (1), Dong Wang (1), Xiaojun Wu (1), Thomas Fang Zheng (1), Javier Tejedor (2)

(1) Tsinghua University, China
(2) Universidad Autónoma de Madrid, Spain

GMM-UBM-based speaker verification heavily relies on well-trained UBMs. In practice, it is not often easy to obtain a UBM that fully matches the acoustic channel in operation. In a previous study, we proposed to address this problem by a novel sequential UBM adaptation approach based on MAP. This work extends the study by applying the sequential approach to speaker model adaptation. In addition, we investigate a new feature-space sequential adaptation approach based on feature MAP linear regression (fMAPLR) and compare it with the previously proposed model-space MAP approach. We find that these two approaches are complementary and can be combined to deliver additional performance gains. The experiments conducted on a time-varying speech database demonstrate that the proposed MAP-fMAPLR approach leads to significant EER reduction with two mismatched UBMs (25% and 39% respectively).

Full Paper

Bibliographic reference.  Wang, Jun / Wang, Dong / Wu, Xiaojun / Zheng, Thomas Fang / Tejedor, Javier (2013): "Sequential model adaptation for speaker verification", In INTERSPEECH-2013, 2460-2464.