The Journal of the Acoustical Society of Korea (한국음향학회지)

The Acoustical Society of Korea (한국음향학회)
권호 표지

A Novel Speech Enhancement Based on Speech/Noise-dominant Decision in Time-frequency Domain

시간-주파수 영역에서 음성/잡음 우세 결정에 의한 새로운 잡음처리

  • 윤석현 (한국과학기술원 전기 및 전자공학과) ;
  • 유창동 (한국과학기술원 전기 및 전자공학과)
  • Published : 2001.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

A novel method to reduce additive non-stationary noise is proposed. The method requires neither the information about noise nor the estimate of the noise statistics from any pause regions. The enhancement is performed on a band-by-band basis for each time frame. Based on both the decision on whether a particular band in a frame is speech or noise dominant and the masking property of the human auditory system, an appropriate amount of noise is reduced using spectral subtraction. The proposed method was tested on various noisy conditions (car noise, Fl6 noise, white Gaussian noise, pink noise, tank noise and babble noise) and on the basis of comparing segmental SNR with spectral subtraction method and visually inspecting the enhanced spectrograms and listening to the enhanced speech, the method was able to effectively reduce various noise while minimizing distortion to speech.

가산적이고 비정상적인 잡음을 줄이는 새로운 방법이 제안되었다. 본 방법은 잡음에 대한 정보나 묵음구간에서의 잡음추정을 필요로 하지 않는다. 잡음처리는 각 시간 프레임에서 주파수대역을 기본으로 하여 수행된다. 어떤 프레임에서 특정한 주파수대역이 음성이 우세한지 혹은 잡음이 우세한지에 대한 결정과 인간청각기의 매스킹 성질을 기반으로 하여, 적절한 양의 잡음을 주파수 차감법을 이용하여 제거한다. 제안된 방법은 다양한 환경에서 (자동차 잡음, Fl6 잡음, 백색 잡음, 핑크 잡음, 탱크 잡음, 혼선잡음) 성능평가가 이루어졌다. 그리고 일반적인 주파수차감법과 비교하여 세그멘탈 신호대 잡음비 (SNR)를 구하고, 시각적 측정 척도인 스펙트로그램과 듣기평가를 통해, 음성왜곡은 줄이면서 효과적으로 잡음을 줄일 수 있음을 알 수 있다.

Keywords

References

  1. IEEE Trans. Acoust., Speech, Signal Processing v.ASSP-27 Suppression of acoustic noise speech using spectral subtraction S. F. Boll
  2. Proc. IEEE v.67 Enhancement and bandwidth compression of noisy speech J. S. Lim;A. V. Oppenheim
  3. Proc. IEEE ICASPP, Washington, DC Enhancement of speech corrupted by acoustic noise M. erouti;R. chwartz
  4. Speech Commun. v.11 Experiments with a nonlinear spectral subtractor(NSS), hidden Markov models and projection, for robust recognition in cars P. Lockwood;J. Boudy
  5. IEEE Trans. Acoust., Speech, Signal Processing v.28 Speech enhancement using a soft-decision noise suppression filter R. J. McAulay;M. L. Malpass
  6. IEEE Trans. Acoust., Speech, Signal Processing v.32 Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator Y. Ephraim;D. Malah
  7. IEEE Trans. Acoust., Speech, Signal Processing v.33 Speech Enhancement Using a Minimum Mean-Square Error Log-Spectral Amplitude Estimator Y. Ephraim;D. Malah
  8. IEEE Trans on Signal Processing v.40 A Bayesian Estimation Approach for Speech Enhancement Using Hidden Markov Models Y. Ephraim
  9. IEEE proceeding v.80 Statistical-Model-Based Speech Enhancement Systems Y. Ephraim
  10. IEEE tran. on speech and audio processing v.6 HMMBased Strategies for Enhancement of Speech Signals Embedded in Nonstationary noise H. Sameti;H. Sheikhzadeh;L. Deng
  11. proc. IEEE ICASSP Speech enhancement using psycho-acoustic criteria D. Tsoukalas;M. Paraskevas;J. Mourjopoulos
  12. proc. IEEE ICASSP Speech parameter extraction in noisy environment using a masking model T. Usagawa;M. Iwata;M. Ebata
  13. IEEE tran. on speech and audio processing v.7 Dual-channel iterative speech enhancement with constrains on an auditory-based spectrum S. Nandkumar;J. H. L. Hansen
  14. IEEE tran. on speech and audio processing v.7 Single Channel Speech Enhancement Based on Masking Property of the Human Auditory System N. Virag
  15. ICASSP Quantile Based Noise Estimation for Spectral subtraction and Wiener Filtering V. Stahl;A. Fischer;R.Bippus
  16. Proc. ICASSP Noise Estimation Techniques for Robust Speech Recognition H. G. Hirsch;C. Ehrlicher
  17. Numerical Analysis D. Kincaid;W. Cheney
  18. Objective Measures of Speech Quality S.Quakenbush;T. Barnwell;M. Clements
  19. Digital Signal Processing Proceedings v.1 A Review of Algorithms for Perceptual Coding of Digital Audio Signals T. Painter;A. Spanias
  20. in foundation of modern auditory theory Critical Bands B. Scharf
  21. Proc. IEEE v.88 Perceptual Coding of Digital Audio T. Painter;A. Spanias
  22. Objective Measures of Speech Quality S. Quakenbush;T. Barnwell;M. Clements