Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Transition-Oriented Hidden Markov Models for Speaker Verification

S. Douglas Peters, Matthieu Hébert, Daniel Boies

Nuance Communications, Montréal, Québec, Canada

In this article, we present a novel mechanism by which more precise voiceprints can be constructed in a typical text-dependent speaker verification system based on a continuous density hidden Markov model (HMM). Typical voiceprints (speaker-dependent HMMs) are first trained using a subscriber's enrollment data. The resulting models are then restructured to permit a modeling of sub-state behavior. At first, the restructured models are functionally equivalent to the conventional voiceprint. Sub-state parameters are then estimated by the re-application of the enrollment data. The resulting speaker-dependent models provide improved speaker verification performance relative to the models with the original topology.


Full Paper

Bibliographic reference.  Peters, S. Douglas / Hébert, Matthieu / Boies, Daniel (2000): "Transition-oriented hidden Markov models for speaker verification", In ICSLP-2000, vol.2, 270-273.