Speaker verification using sparse representation classification

Sparse representations of signals have received a great deal of attention in recent years, and the sparse representation classifier has very lately appeared in a speaker recognition system. This approach represents the (sparse) GMM mean supervector of an unknown speaker as a linear combination of an over-complete dictionary of GMM supervectors of many speaker models, and 1-norm minimization results in a non-zero coefficient corresponding to the unknown speaker class index. Here this approach is tested on large databases, introducing channel-/session-variability compensation, and fused with a contemporary GMM-SVM system. Evaluations on the NIST 2006 SRE database show that when the outputs of the MFCC GMM-SVM-NAP based classifier are fused with the MFCC GMM-Sparse Representation ClassifierNAP (GMM-SRC-NAP) based classifier, a baseline EER of 6.56% can be reduced to 2.65%, significantly improving the performance of the speaker verification system.

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Jia Min Karen Kua, Eliathamby Ambikairajah, Julien Epps, Roberto Togneri
• Keywords: ICASSP 2011, Signal Processing, Sparse Representation, Sparse Representation Classifier, Unknown Speaker