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}
}