Speaker verification based on SVDD

A new speaker verification method based on SVDD is proposed from another viewpoint to solve the problem such that the recognition rate of the speaker verification system based on GMM is not very high. The traditional hard decision method is also changed, instead a new soft decision means based on the sample acceptance rate is introduced, whose main advantage is normalized the 'probability' or 'confidence' to the value (0,1) and the threshold is comparative steady so as to be easy setting. Experiments are based on TIMIT database, selecting 50 people, with cross validation method, taking EER for the system performance evaluation criteria, comparing SVDD with GMM systems in unified threshold or independent threshold. Experiments result show that this method obviously improves the recognition accuracy and robustness; the running time of the system based on SVDD reduced 26.2% and EER decreased 22.5%; furthermore, when under the conditions of insufficient training samples, SVDD gain more obvious advantage over GMM in teams of training time, running time and recognition accuracy.

[1]  Wu Zhaohui,et al.  Support vector domain description for speaker recognition , 2001, Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584).

[2]  Amit Banerjee,et al.  A support vector method for anomaly detection in hyperspectral imagery , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Zhou Yong,et al.  Fault Condition Detection Based on Wavelet Packet Transform and Support Vector Data Description , 2008, 2008 Second International Symposium on Intelligent Information Technology Application.

[4]  Xu Yong,et al.  A Novel Model of one-class Bearing Fault Detection using SVDD and Genetic Algorithm , 2007, 2007 2nd IEEE Conference on Industrial Electronics and Applications.

[5]  Jun Wang,et al.  A Practical and Robust Way to the Optimization of Parameters in RBF Kernel-Based One-Class Classification Support Vector Methods , 2009, 2009 Fifth International Conference on Natural Computation.

[6]  Amit Banerjee,et al.  Fast Hyperspectral Anomaly Detection via SVDD , 2007, 2007 IEEE International Conference on Image Processing.

[7]  Chi-Kai Wang,et al.  A novel approach of feature classification using Support Vector Data Description combined with interpolation method , 2008, 2008 34th Annual Conference of IEEE Industrial Electronics.

[8]  Chandan Srivastava,et al.  Support Vector Data Description , 2011 .

[9]  Lei Guo,et al.  Fuzzy recognition method for radar target based on KPCA and SVDD , 2007, International Symposium on Multispectral Image Processing and Pattern Recognition.

[10]  Robert P. W. Duin,et al.  Support vector domain description , 1999, Pattern Recognit. Lett..