Fusion of cross stream information in speaker verification
Fawaz Waselallah Alsaade, A. Malegaonkar, A. M. Ariyaeeinia · University of Hertfordshire Research Archive (University of Hertfordshire) · 2005
This paper addresses the performance of various statistical data fusion techniques for combining the complementary score information in speaker verification. The complementary veri-fication scores are based on the static and delta cepstral fea-tures. Both LPCC (Linear prediction-based cepstral coeffi-cients) and MFCC (mel-frequency cepstral coefficients) are considered in the study. The experiments conducted using a GMM-based speaker verification system, provides valuable information on the relative effectiveness of different fusion methods applied at the score level. It is also demonstrated that a higher speaker discrimination capability can be achieved by applying the fusion at the score level rather than at the feature level. 1.