论文信息 - Spectral Estimation for Noise Robust Speech Recognition

Spectral Estimation for Noise Robust Speech Recognition

We present results on the recognition accuracy of a continuous speech, speaker independent HMM recognition system that incorporates a novel noise reduction algorithm. The algorithm is a minimum mean square error estimation tailored for a filter-bank front-end. It introduces a significant improvement over similar published algorithms by incorporating a better statistical model for the filter-bank log-energies, and by attempting to jointly estimate the log-energies vector rather than individual components. The algorithm was tested with SRI's recognizer trained on the official speaker-independent "Resource management task" clean speech database. When tested with additive white gaussian noise, the noise reduction achieved by the algorithm is equivalent to a 13 dB SNR improvement. When tested with desktop microphone recordings, the error rate at 13 dB SNR is only 40% higher than that with close-talking microphone at 31 dB SNR.

Mitch Weintraub | Adoram Erell

[1] Hy Murveit,et al. Linguistic constraints in hidden Markov model based speech recognition , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[2] Steven F. Boll,et al. Optimal estimators for spectral restoration of noisy speech , 1984, ICASSP.

[3] D. M. Green,et al. Signal detection theory and psychophysics , 1966 .

[4] Patti Price,et al. The DARPA 1000-word resource management database for continuous speech recognition , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[5] R. McAulay,et al. Speech enhancement using a soft-decision noise suppression filter , 1980 .

[6] S. Boll,et al. Suppression of acoustic noise in speech using spectral subtraction , 1979 .

[7] Dirk Van Compernolle. Noise adaptation in a hidden Markov model speech recognition system , 1989 .

[8] Ephraim. Speech enhancement using a minimum mean square error short-time spectral amplitude estimator , 1984 .

[9] D. van Compernolle. Spectral estimation using a log-distance error criterion applied to speech recognition , 1989, ICASSP.

[10] David Malah,et al. Speech enhancement using a minimum mean-square error log-spectral amplitude estimator , 1984, IEEE Trans. Acoust. Speech Signal Process..