ISCA Archive ICSLP 2000
ISCA Archive ICSLP 2000

A MAP approach, with synchronous decoding and unit-based normalization for text-dependent speaker verification

Johnny Mariethoz, Johan Lindberg, Frédéric Bimbot

This paper presents an overview of some of the research tracks in text-dependent speaker verification followed by the Picasso Project (Research Work Package). We focus successively on the training algorithm (based on a MAP approach), the state-sequence decoding procedure (by Synchronous Alignment) and the score normalization (unit-based z-normalization). On short utterances of 1 to 5 syllables (Polyvar command words), we obtain an error rate of 5.6 % with 2 training sessions, which can be brought down to 3.3% with 3 additional sessions in incremental trainmg mode.


Cite as: Mariethoz, J., Lindberg, J., Bimbot, F. (2000) A MAP approach, with synchronous decoding and unit-based normalization for text-dependent speaker verification. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 2, 286-289

@inproceedings{mariethoz00_icslp,
  author={Johnny Mariethoz and Johan Lindberg and Frédéric Bimbot},
  title={{A MAP approach, with synchronous decoding and unit-based normalization for text-dependent speaker verification}},
  year=2000,
  booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
  pages={vol. 2, 286-289}
}