| H.A. Murthy, F. Beaufays, L.P. Heck, M. Weintraub, "Robust text-independent speaker identification over telephone channels", IEEE Trans. on Speech and Audio Processing, vol. 7, no. 5 , 1999, pp. 554-568. |
....system [1] In addition, the typically limited amount of training data further accentuates the problem. The issue of acoustic mismatches can be tackeled at different levels: speech features can be extracted that are less sensitive to channel effects than the traditional cepstrum (see e.g. [2, 13]) the effect of mismatches can be reduced via cepstral mean bias removal (see e.g. 3 6] the speaker models can be transformed to compensate for the mismatches, rescoring techniques can be used to normalize the speaker scores and reduce the channel effects (see e.g. 7] etc. This paper ....
....Assuming that the acoustic coverage of Sennheiser data is similar to that of data collected from a telephone unit under similar conditions (same amount of data) we could apply this transformation to speaker models trained for other telephone databases. This approach is further described in [13]. It gave good results but was outperformed by the variance transformation described in the next section. 7. SPEAKER MODEL TRANSFORMATION This transformation can be seen as an extension of the affine transformation mentioned previously. It translates the variances of the speaker models so as to ....
[Article contains additional citation context not shown here]
H.A. Murthy, F. Beaufays, L.P. Heck, M. Weintraub, "Robust Text-Independent Speaker Identification over Telephone Channels", in preparation - to be submitted to IEEE Trans. Speech and Audio Proc..
No context found.
H.A. Murthy, F. Beaufays, L.P. Heck, M. Weintraub, "Robust text-independent speaker identification over telephone channels", IEEE Trans. on Speech and Audio Processing, vol. 7, no. 5 , 1999, pp. 554-568.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC