Fusing acoustic, phonetic and data-driven systems for text-independent speaker verification

This paper describes our recent efforts in exploring datadriven high-level features and their combination with low-level spectral features for speaker verification. In particular, we compare the phonetic and data-driven approaches and study their complementarity with short-term acoustic approach. Our objective is to show that data-driven units automatically acquired from the speech data, can be used like phonemes to extract highlevel features and to bring complementary speaker-specific information that can therefore provide improvements when fused with acoustic systems. Results obtained on the NIST 2006 Speaker Recognition Evaluation data show that the combination of the phonetic, data-driven and Gaussian Mixture Models (GMM) systems brings a 27% relative reduction of the EER in comparison to the baseline GMM system.