The Journal of the Acoustical Society of Korea

한국음향학회 (The Acoustical Society of Korea)
권호 표지

음성신호개선을 위한 임계대역 웨이블렛 패킷 기반의 스펙트럼 차감법

Critical Banded Wavelet Packet-Based Spectral Subtractions for Speech Enhancement

  • Chang, Sung-Wook (School of Electrical and Computer Engineering, Hanyang University) ;
  • Yang, Sung-Il (School of Electrical and Computer Engineering, Hanyang University)
  • 발행 : 2004.12.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

In this paper, we propose a critical banded wavelet packet-based spectral subtraction for speech enhancement. Critical banded wavelet packet, which reflects the human auditory system, may lead to minimization of intelligibility loss and quality improvement of the enhanced speech in the spectral domain, when combined with an appropriate spectral subtraction gain function. The proposed method shows better performance than the conventional one in comparative assessments. We also show that, for effective evaluation of enhanced speech, it is essential to consider the characteristics of speech quality measures.

키워드

참고문헌

  1. Y. Ephraim and H. L. Van Trees, 'A Signal Subspace Approach forSpeech Enhancement,' IEEE Trans. on Speech and Audio Processing,3(4),pp.251-266,JuIy, 1995 https://doi.org/10.1109/89.397090
  2. M. Klein and P. Kabal, 'Signal Subspace Speech Enhancement withPerceptual Post filtering,' Proc. IEEE Int. Conf. Acoustics Speechand Signal Processing, pp. 537-540 May 2002
  3. F. Jabloun and B. Champagne, 'A Perceptual Signal SubspaceApproach for Speech Enhancement in Colored Noise,' Proc IEEE Int.Conf. Acoustics, Speech and Signal Processing, 1 pp. 569-572 2002
  4. Y. Hu and P. Loizou, 'Perceptual Weighting Motivated Subspacebased Speech Enhancement Approach,' Proc. of Int Conf onSpoken Language Processing, pp. 1797-1800, 2002
  5. S. Chang, S. Jung, Y. Kwon, and S. Yang, 'Speech Enhancementusing Wavelet Packet Transform,' Proc. of Int. Conf. on SpokenLanguage Processing, pp. 1809-1812, 2002
  6. S. Chang, Y. Kwon, S. Jung, S. Yang and K. Lee, 'SpeechEnhancement using Level Adapted Wavelet Packet with AdaptiveNoise Estimation,' The Joumal of the Acoustical Society of Korea22(2E), pp. 87-92, 2003
  7. S. Chang, Y. Kwon, SU Jung and S. Yang, 'Adaptive Wavelet basedSpeech Enhancement wlth Robust VAD in NonStationary NoiseEnvironment,' The Journal of the Acoustlcal Society of Korea, 22(4E)2003
  8. M. V. Wickerhauser, Adapted Wavelet Analysis from Theory to Software, AK Peters, 1994
  9. I. Cohen, 'Enhancement of Speech using Bark-ScaIed Wavelet Packet Decomposition,' EUROSPEECH 2001 pp 3-7 2001
  10. H. G. Hirsch, 'Estimation of Noise Spectrum and its Application toSNR Estimation and Speech Enhancement,' Technical Report TR-93-012, International Computer Science Institute, Berkeley USA 1993
  11. P. Noll, 'Adaptive Quantization in Speech Coding Systems,' Proc.Int. Zurich Seminar on Dlgital Communications, pp. B3.1-B3.6 Oct.1974
  12. S. R. Quackenbush, T. P. Barnwell, M. A. Clements, ObjectiveMeasures of Speech Quality, Prentice-Hall, NJ, 1988
  13. S. Wang and A. Gersho, 'An Objective Measure for PredictingSubjective Quality of Speech Coders,' IEEE Journal on SelectedAreas in Communications, 10(5), June, 1992
  14. D. G. Jamieson, L. Deng, M. Price, V. Parsa and J. Till, 'Interactionof Speech Disorders with Speech Coders: Effects on SpeechIntelligibility,' Proc. of Int. Conf. on Spoken Language Processing, pp.737-740, 1996
  15. J. H. L. Hansen and B. L. Pellom, 'An Effective Quality EvaluationProtocol for Speech Enhancement Algorithms,'Proc. of Int. Conf. onSpoken Language Processing , pp. 2819-2822, 1998
  16. J. Deller, J. Proakis, J. H. L. Hansen, Discrete-Time Processing of Speech Signals, McMillan Series for Prentice Hall, New York, NY,1993
  17. T. P. Barnwell and W. D. Voiers, 'An analysis of objective measuresfor user acceptance of voice communication systems,' DCA FinalTechnical Report, No. DCA100-78-C-0003, Sept. 1979
  18. T. P. Barnwell, M. A. Clements, S. R. Quackenbush et. al, 'Improvedobjective measures for speech quality testing,' DCA Final Technical Report, No DCA100-83-C-0027, Sept. 1984
  19. T. P. Barnwell, 'Improved objective quality for low bit speechcompression,' National Science Foundation, Final Technical Report, ECS-8016712, 1985
  20. D Klatt, 'Prediction of Perceived Phonetic Distance from CriticalBand Spectra: A First Step,' Proc. IEEE Int. Conf. Acoustics, Speechand Signal Processing, pp. 1278-1281, 1982
  21. ITU-T Recommendation P.862, Perceptual Evaluation of Speech Quality (PESQ), International Telecommunication Union, Feb. 2001
  22. P. Kabal, 'Demo and Matlab Toolbox for [2],' http://www.tsp.ece.mcgill.ca/Kabal/Papers/2002/K1einC2002-demo/
  23. B. Pellom, 'Matlab toolbox for Objective Speech QualityAssessment,' CSLU Robust Speech Processing Laboratory, http://cslr.colorado.edu/rspl/rspl_software.html
  24. P. E. Papamichalis, Practical Approaches to Speech Coding,Prentice Hall, England Cliffs, NJ, 1987