Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

A Discriminative Method for Speaker Verification Using the Difference Information

Zhenchun Lei, Yingchun Yang, Zhaohui Wu

Zhejiang University, China

In this paper, a discriminative method is proposed for speaker verification. An utterance can be mapped into a matrix by computing the difference to a codebook, and then expand the mapped matrix to a vector as the input of support vector machines for speaker verification. The Gaussian mixture model-based method is also constructed by utilizing its nature. The mapped vector indicates the utterance’s fitness to the codebook. Compared with the derivative operation in the famous fisher kernel the difference operation is used in our method. Experiments were run on the YOHO database in the text-independent case show that the new method is superior to the conventional GMM for speaker verification.

Full Paper

Bibliographic reference.  Lei, Zhenchun / Yang, Yingchun / Wu, Zhaohui (2006): "A discriminative method for speaker verification using the difference information", In INTERSPEECH-2006, paper 1952-Mon3A1O.2.