Noise reduction system using time-delay neural network

시간지연 신경회로망을 이용한 잡음제거 시스템

  • Choi Jae-Seung (Digital Technology Research Center, Kyungpook National University)
  • 최재승 (경북대학교 디지털기술연구소)
  • Published : 2005.05.01

Abstract

On the research field for speech signal, neural network mainly uses for the category classification in speech recognition and applies to signal processing. Accordingly, this paper proposes a noise reduction system using a time-delay neural network, which implements the mapping from the space of speech signal degraded by noise to the space of clean speech signal. It is confirmed that this method is effective for speech degraded not only by white noise but also by colored noise using the noise reduction system, which restores the amplitude component of fast Fourier transform.

음성신호를 대상으로 하는 연구 분야에서 신경회로망은 주로 음성인식 등의 카테고리 분류의 목적으로 사용되며 신호처리의 응용에도 유망하다. 따라서 본 논문에서는 신경회로망에 시간구조를 취한 시간지연 신경회로망을 이용하여 잡음이 중첩된 음성신호의 공간으로부터 잡음이 없는 음성신호의 공간으로 사상을 실행함으로써 잡음을 제거하는 것을 목적으로 한다. 본 논문은 푸리에 변환의 진폭성분을 복원하는 잡음제거의 알고리즘을 사용하여 백색잡음 및 유색잡음에 대해서 본 수법의 유효성을 확인한다.

Keywords

References

  1. K. K. Paliwal, 'Neural net classifiers for robust speech recognition under noisy environments', IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 1, pp. 429-432, April 1990 https://doi.org/10.1109/ICASSP.1990.115737
  2. J. T. Chien, L. M. Lee, and H. C. Wang, 'Noisy speech recognition by using variance adapted hidden Markov models', IEE Electronics Letters, Vol. 31. No. 18, pp. 1555- 1556, 1995 https://doi.org/10.1049/el:19951066
  3. W. G. Knecht, M. E. Schenkel, and G. S. Moschytz, 'Neural network filters for speech enhancement,' IEEE Trans. Speech and Audio Processing, Vol.3, No.6, pp. 433-438, 1995 https://doi.org/10.1109/89.482210
  4. S. Tamura, 'An analysis of a noise reduction neural network', IEEE International Conference on Acoustics, Speech, and Signal Processing. Vol. 89, No.3, pp. 2001-2004, 1989 https://doi.org/10.1109/ICASSP.1989.266851
  5. J. S. Lim, 'Evaluation of a correlation subtraction method for enhancing speech degraded by additive white noise', IEEE Trans. Acoust., Speech, Signal Processing. Vol. 6, No.5, pp. 471-472, 1978
  6. S. F. Boll, 'Suppression of acoustic noise in speech using spectral subtraction', IEEE Trans. Acoust., Speech, Signal Processing. Vol. 27, No. 2, pp. 113-120, 1979 https://doi.org/10.1109/TASSP.1979.1163209
  7. T. V. Sreenivas and P. Kirnapure, 'Codebook constrained wiener filtering for speech enhancement,' IEEE Trans. Speech and Audio Processing, Vol.4, No.5, pp. 383-389, 1996 https://doi.org/10.1109/89.536932
  8. S. Oh, V. Viswanathan, and P. Papamichalis, 'Hands-free voice communication in an automobile with a microphone array', IEEE International Conference on Acoustics, Speech, and Signal Processing. Vol. 92, No.1, pp. 281-284, 1992 https://doi.org/10.1109/ICASSP.1992.225916
  9. B. Widrow, et al., 'Adaptive noise cancelling: Principles and applications', Proc. IEEE, Vol. 63, No. 12, pp. 1692-1716, 1975 https://doi.org/10.1109/PROC.1975.10036
  10. M. R. Sambur, 'Adaptive noise cancelling for speech signals', IEEE Trans. Acoust., Speech, Signal Processing. Vol. 26, No.5, pp. 419-423, 1978 https://doi.org/10.1109/TASSP.1978.1163137
  11. A. Ishida and H. Gobata, 'Speech/Non-speech Discrimination under Real Life Environments'. J. Acoust. Soc. Japan, Vol. 47, No. 12, pp. 911-917, 1991
  12. Y. Wu, Y. Li, 'Robust speech/non-speech detection in adverse conditions using the fuzzy polarity correlation method', IEEE International Conference on Systems, Man, and Cybernetics, Oct. pp. 2935-2939, 2000 https://doi.org/10.1109/ICSMC.2000.884446
  13. M. Miyatake, H. Sawai, and K Shikano, 'Training Methods and Their Effects for Spoting Japanese Phenomes Using Time-Delay Neural Networks', IEICE, Vol. J73-D-II, No.5, pp. 699-706, 1990
  14. K Itoh, N. Kitawaki, and K. Kakehi, 'A Study of Objective Quality Measures for Digital Speech Waveform Coding Systems', IEICE, Vol. J66-A, No.3, pp. 274-281, 1983