Browse > Article

A Spectral Compensation Method for Noise Robust Speech Recognition  

Cho, Jung-Ho (Dept. of Digital Electronics, Dongseoul college)
Publication Information
전자공학회논문지 IE / v.49, no.2, 2012 , pp. 9-17 More about this Journal
Abstract
One of the problems on the application of the speech recognition system in the real world is the degradation of the performance by acoustical distortions. The most important source of acoustical distortion is the additive noise. This paper describes a spectral compensation technique based on a spectral peak enhancement scheme followed by an efficient noise subtraction scheme for noise robust speech recognition. The proposed methods emphasize the formant structure and compensate the spectral tilt of the speech spectrum while maintaining broad-bandwidth spectral components. The recognition experiments was conducted using noisy speech corrupted by white Gaussian noise, car noise, babble noise or subway noise. The new technique reduced the average error rate slightly under high SNR(Signal to Noise Ratio) environment, and significantly reduced the average error rate by 1/2 under low SNR(10 dB) environment when compared with the case of without spectral compensations.
Keywords
speech recognition; spectral compensation; noise subtraction; spectral tilt;
Citations & Related Records
연도 인용수 순위
  • Reference
1 H. Bourlard and S. Dupont, A new ASR approach based on independent processing and recombination of partial frequency bands, ICSLP'96, Philadelphia, vol. 1,pp. 426-429, Oct. 1996.
2 H. Hermansky, Perceptual linear prediction (PLP) analysis of speech, Proc. JASA, pp. 1738-1752, Apr. 1990.
3 H. Hermansky, RASTA processing of speech, IEEE Trans. Speech Audio processing, vol. 2, pp. 578-589, Oct. 1994.   DOI   ScienceOn
4 M. J. Gales, S. Young, Robust speech recognition using parallel model combination, IEEE Trans. Speech Audio processing, vol. 4. pp. 352-359, Sep. 1996.   DOI   ScienceOn
5 P. J. Moreno, B. Raj and R. M. Stern, A vector Taylor series approach for environmentindependent speech recognition, ICASSP'96, Atlanta, vol. 2, pp. 733-736, May, 1996.
6 S. V. Vaseghi and B. P. Milner, Noise compensation methods for hidden Markov model speech recognition in adverse environments, IEEE Trans. Speech and Audio Processing, vol. 5, No. 1, pp. 11-21, Jan. 1997.   DOI   ScienceOn
7 D. C. Popescu and I. Zeljkovic, Kalman filtering of colored noise for speech enhancement, ICSLP'96, Philadelphia, vol. 1, pp.426-429, Oct. 1996.
8 S. F. Boll, Suppression of acoustic noise in speech using spectral subtraction, IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-27, no. 2, pp. 113-120, Apr. 1979.
9 D. Naik, Pole-filtered cepstral mean subtraction, ICSLP'95, Detroit, vol. 1, pp. 157-160, May, 1995.
10 J. Chen, K. K. Paliwal and S. Nakamura, Sub-band based additive noise removal for robust speech recognition, Proc. Eurospeech, pp. 70-73, 2001.
11 L. R. Rabiner and R. W. Schafer, Digital Processing of Speech Signals, Prentice-Hall, 1978.
12 A. Acero and R. M. Stern, Environmental robustness in automatic speech recognition, Proc. ICASSP90, pp. 849-852, Apr. 1990.
13 A. Oppenheim and D. Johnson, Discrete representation of signals, Pro. of IEEE, vol. 60, no. 6, pp. 681-691, June, 1972.   DOI
14 P. A. Regalia, S. K. Mitra and P. P. Vaidyanathan, The digital all-pass filter: A versatile signal processing building block, Pro. of IEEE, vol. 76, no. 1, pp. 19-37, Jan. 1988.   DOI   ScienceOn