ISCA Archive ICSLP 2000
ISCA Archive ICSLP 2000

Speaker verification in noise using temporal constraints

Néstor Becerra Yoma, Tarciano Facco Pegoraro

This paper addresses the problem of state duration modeling in combination with spectral subtraction and Rasta filtering to cancel both additive and convolutional noise in a text-dependent speaker verification task. The results presented in this paper suggest that temporal constraints can lead to reductions of 30 and 14% in the error rates at SNR equal to 0 and 6dB, respectively, without noise canceling techniques. However, with noise canceling methods, temporal restrictions give a lower improvement. The results here shown propose that state duration modeling can be useful in those cases when the noise reduction is low.


Cite as: Yoma, N.B., Pegoraro, T.F. (2000) Speaker verification in noise using temporal constraints. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 3, 1021-1024

@inproceedings{yoma00b_icslp,
  author={Néstor Becerra Yoma and Tarciano Facco Pegoraro},
  title={{Speaker verification in noise using temporal constraints}},
  year=2000,
  booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
  pages={vol. 3, 1021-1024}
}