Linear and non linear kernel GMM supervector machines for speaker verification

This paper presents a comparison between Support Vector Machines (SVM) speaker verification systems based on linear and non linear kernels defined in GMM supervector space. We describe how these kernel functions are related and we show how the nuisance attribute projection (NAP) technique can be used with both of these kernels to deal with the session variability problem. We demonstrate the importance of GMM model normalization (M-Norm) especially for the non linear kernel. All our experiments were performed on the core condition of NIST 2006 speaker recognition evaluation (all trials). Our best results (an equal error rate of 6.3%) were obtained using NAP and GMM model normalization with the non linear kernel. Index Terms: Speaker recognition, Gaussian mixture model, support vector machine, Linear kernel, Non linear kernel, Nuisance attribute projection, M-Norm.

[1]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[2]  Douglas A. Reynolds,et al.  Speaker Verification Using Adapted Gaussian Mixture Models , 2000, Digit. Signal Process..

[3]  Frédéric Bimbot,et al.  D-MAP: a distance-normalized MAP estimation of speaker models for automatic speaker verification , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[4]  M. Do.  Fast approximation of Kullback-Leibler distance for dependence trees and hidden Markov models , 2003, IEEE Signal Processing Letters.

[5]  Nuno Vasconcelos,et al.  A Kullback-Leibler Divergence Based Kernel for SVM Classification in Multimedia Applications , 2003, NIPS.

[6]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[7]  Patrick Kenny,et al.  Experiments in speaker verification using factor analysis likelihood ratios , 2004, Odyssey.

[8]  William M. Campbell,et al.  Advances in channel compensation for SVM speaker recognition , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[9]  Gérard Chollet,et al.  Support Vector Gmms for Speaker Verification , 2006, 2006 IEEE Odyssey - The Speaker and Language Recognition Workshop.

[10]  Douglas E. Sturim,et al.  SVM Based Speaker Verification using a GMM Supervector Kernel and NAP Variability Compensation , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.