Sixth International Conference on Spoken Language Processing
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.
Bibliographic reference. Yoma, NÚstor Becerra / Pegoraro, Tarciano Facco (2000): "Speaker verification in noise using temporal constraints", In ICSLP-2000, vol.3, 1021-1024.