7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

Noise Adaptive Speech Recognition with Acoustic Models Trained from Noisy Speech Evaluated on Aurora-2 Database

Kaisheng Yao, Kuldip K. Paliwal, Satoshi Nakamura

ATR Spoken Language Translation Research Laboratories, Japan

In this paper, we apply the noise adaptive speech recognition for noisy speech recognition in non-stationary noise to the situation that acoustic models are trained from noisy speech. We justify it by that the noise adaptive speech recognition includes iterative processes between a noise parameter estimation step and a model adaptation step, which can possibly do non-linear mapping between the original training space and that for recognition. Experiments were performed on Aurora-2 task with multi-conditional training set which includes noisy utterances. Through experiments, we observed that the noise adaptive speech recognition can have better performance than the baseline system trained from multi-conditional training set without noise adaptive speech recognition.


Full Paper

Bibliographic reference.  Yao, Kaisheng / Paliwal, Kuldip K. / Nakamura, Satoshi (2002): "Noise adaptive speech recognition with acoustic models trained from noisy speech evaluated on Aurora-2 database", In ICSLP-2002, 2437-2440.