EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology

Aalborg, Denmark
September 3-7, 2001


Linear Interpolation of Cepstral Variance for Noisy Speech Recognition

Tai-Hwei Hwang (1), Kuo-Hwei Yuo (2), Hsiao-Chuan Wang (2)

(1) Industrial Technology Research Institute, Taiwan
(2) National Tsing Hua University, Taiwan

Speech model combination with the background noise has been shown effective to improve the pattern classification rate of noisy speech. The model combination can be performed by the addition of the spectral statistics such as the means and the variances. Since the speech feature for pattern classification has to be expressed in the cepstral domain, the combined spectral statistics have to be transferred into the cepstral domain for speech recognition. In our previous study, we have proposed a direct adaptation scheme of the cepstral variance that is without the mapping from the spectral domain to the cepstral domain. In this paper, an improved version to perform the adaptation is proposed. From the study, it is observed that the adapted variance can be expressed as a linear interpolation of the speech and the noise variances to obtain a comparable recognition rate that is obtained with the mapping process. Due to the direct adaptation of the variances, a lot of computation can be reduced to perform the environmental adaptation.

Full Paper

Bibliographic reference.  Hwang, Tai-Hwei / Yuo, Kuo-Hwei / Wang, Hsiao-Chuan (2001): "Linear interpolation of cepstral variance for noisy speech recognition", In EUROSPEECH-2001, 877-880.