Noise suppression and channel equalization preprocessor for speech and speaker recognizers: method and apparatus
作者： Alan Lawrence Higgins , Jack E. Porter , Steven F. Boll
DOI:
关键词:
摘要: A method for performing noise suppression and channel equalization of a noisy voice signal comprising the steps sampling at predetermined rate f s ; segmenting sampled into plurality frames having number samples per frame, over temporal window; generating an N-point spectral sample representation each frames; determining magnitude histogram energy associated with particular frequency; detecting peak amplitude which corresponds to threshold N frequency response C by geometric mean all exceeding subtracting from magnitudes point provide suppressed sequence; applying blind deconvolution samples; transforming deconvolved sequence representation; shifting in time amount; adding shifted period corresponding window signal.
google.de 参考文章(7)
Zhang Zhijie, Zu Jing, Zhang Aiping, Stabilized solutions and multiparameter optimization technique of deconvolution international conference on signal processing. pp. 168- 171 ,(1998) , 10.1109/ICOSP.1998.770176
J. de Veth, L. Boves, Comparison of channel normalisation techniques for automatic speech recognition over the phone international conference on spoken language processing. ,vol. 4, pp. 2332- 2335 ,(1996) , 10.1109/ICSLP.1996.607275
C. Avendano, H. Hermansky, On the effects of short-term spectrum smoothing in channel normalization IEEE Transactions on Speech and Audio Processing. ,vol. 5, pp. 372- 374 ,(1997) , 10.1109/89.593318
S. Boll, Suppression of acoustic noise in speech using spectral subtraction IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 27, pp. 113- 120 ,(1979) , 10.1109/TASSP.1979.1163209
H. Hermansky, N. Morgan, RASTA processing of speech IEEE Transactions on Speech and Audio Processing. ,vol. 2, pp. 578- 589 ,(1994) , 10.1109/89.326616
T.G. Stockham, T.M. Cannon, R.B. Ingebretsen, Blind deconvolution through digital signal processing Proceedings of the IEEE. ,vol. 63, pp. 678- 692 ,(1975) , 10.1109/PROC.1975.9800
D. Hardt, K. Fellbaum, Spectral subtraction and RASTA-filtering in text-dependent HMM-based speaker verification international conference on acoustics, speech, and signal processing. ,vol. 2, pp. 867- 870 ,(1997) , 10.1109/ICASSP.1997.596073