Analysis of Speaker Verification System Using Support Vector Machine

The integration of GMM- super vector and Support Vector Machine (SVM) has become one of most popular strategy in text-independent speaker verification system.  This paper describes the application of Fuzzy Support Vector Machine (FSVM) for classification of speakers using GMM-super vectors. Super vectors are formed by stacking the mean vectors of adapted GMMs from UBM using maximum a posteriori (MAP). GMM super vectors characterize speaker’s acoustic characteristics which are used for developing a speaker dependent fuzzy SVM model. Introducing fuzzy theory in support vector machine yields better classification accuracy and requires less number of support vectors. Experiments were conducted on 2001 NIST speaker recognition evaluation corpus. Performance of GMM-FSVM based speaker verification system is compared with the conventional GMM-UBM and GMM-SVM based systems.  Experimental results indicate that the fuzzy SVM based speaker verification system with GMM super vector achieves better performance to GMM-UBM system. Â