ISCA Archive ASRIV 1994
ISCA Archive ASRIV 1994

Comparison of hidden Markov model techniques for automatic speaker verification

Johan de Veth, Hervé Bourlard

In this paper, we compare two alternative approaches for speaker verification based on hidden Markov model (HMM) technology: single Gaussian HMMs and tied multi-Gaussian HMMs. We tested each system using a database of connected digit strings recorded over local and long-distance telephone lines. According to our experiments, tied-mixture models were able to perform better than the single Gaussian approach provided that sufficient training data were available. Results will be discussed for both text-dependent and text-independent speaker verification.