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 utterances 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.
Cite as: Lei, Z., Yang, Y., Wu, Z. (2006) A discriminative method for speaker verification using the difference information. Proc. Interspeech 2006, paper 1952-Mon3A1O.2, doi: 10.21437/Interspeech.2006-162
@inproceedings{lei06_interspeech,
author={Zhenchun Lei and Yingchun Yang and Zhaohui Wu},
title={{A discriminative method for speaker verification using the difference information}},
year=2006,
booktitle={Proc. Interspeech 2006},
pages={paper 1952-Mon3A1O.2},
doi={10.21437/Interspeech.2006-162}
}