5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Adaptation of Time Differentiated Cepstrum for Noisy Speech Recognition

Tai-Hwei Hwang (1), Lee-Min Lee (2), Hsiao-Chuan Wang (1)

(1) Department of Electrical Engineering, National Tsing-Hua University, Hsinchu, Taiwan
(2) Department of Electrical Engineering, Mingchi Institute of Technology, Taipei Hsien, Taiwan

In this paper, a noise compensation algorithm using the first order approximation of cepstral function is presented. The derivative term is replaced by the difference of cepstra for the adaptation of wide range variation of noise power. The differences of cepstral mean vectors between the clean and noisy version, termed as the deviation vector, are applied to adapt cepstrum and delta cepstrum. The experimental results show that using deviation vector to adapt the cepstral coefficients can gain a significant improvement over the method based on weighted projection measure. Further improvement can be made by jointly adapting the cepstrum and delta cepstrum.

Full Paper

Bibliographic reference.  Hwang, Tai-Hwei / Lee, Lee-Min / Wang, Hsiao-Chuan (1997): "Adaptation of time differentiated cepstrum for noisy speech recognition", In EUROSPEECH-1997, 1075-1078.