5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

HMM Compensation for Noisy Speech Recognition Based on Cepstral Parameter Generation

Takao Kobayashi (1), Takashi Masuko (1), Keiichi Tokuda (2)

(1) Precision and Intelligence Laboratory, Tokyo Institute of Technology, Yokohama, Japan
(2)Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan

This paper proposes a technique for compensating both static and dynamic parameters of continuous mixture density HMM to make it robust to noise. The technique is based on cepstral parameter generation from HMM using dynamic parameters. The generated cepstral vector sequences of speech and noise are combined to yield noisy speech cepstral vector sequence, and the dynamic parameters are calculated from the obtained cepstral vector sequence. Model parameters for noisy speech HMM are obtained using the statistics of the noisy speech parameter sequences. We use the mixture transition probability for estimating the parameters of the compensated model. Experimental results show the effectiveness of the proposed technique in the noisy speech recognition.

Full Paper

Bibliographic reference.  Kobayashi, Takao / Masuko, Takashi / Tokuda, Keiichi (1997): "HMM compensation for noisy speech recognition based on cepstral parameter generation", In EUROSPEECH-1997, 1583-1586.