정보처리학회논문지B (The KIPS Transactions:PartB)

한국정보처리학회 (Korea Information Processing Society)
권호 표지
DOI QR코드

DOI QR Code

이산 웨이브렛 변환을 이용한 유효 음성 추출에 관한 연구

A Study on Extracting Valid Speech Sounds by the Discrete Wavelet Transform

  • 김진옥 (성균관대학교 대학원 전기전자 및 컴퓨터공학부) ;
  • 황대준 (성균관대학교 전기전자 및 컴퓨터공학부) ;
  • 백한욱 (American-Panel Corporation in USA 연구원) ;
  • 정진현 (광운대학교 정보제어공학과)
  • 발행 : 2002.04.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

유효한 무성음이 시스템 노이즈와 합성됐을 경우 유효한 무성음 추출에 많은 어려움이 있으나 본 논문에서는 유효한 무성음 추출에 있어 이산 웨이브렛 변환을 이용한 신호 해석 내용을 기반으로 주파수와 그 위치를 블록별로 머징 규칙으로 유효 여부를 결정하기 때문에 노이즈가 많은 환경에서도 유효한 무성음 추출이 가능하다. 머징 알고리즘은 음성만으로도 처리 매개변수를 결정할 수 있고 시스템 잡음에 대하여서도 독립적이기 때문에 유효한 음성을 추출하는데 매우 효과적이다. 실험 결과를 통하여 유효한 음성 추출 처리 과정에서 보다 향상된 결과를 보이고 있으며 특히 고주파 노이즈에 대한 강한 적응력을 제시하고 시스템 구현에도 용이한 시스템 튜닝을 가능케 한다.

The classification of the speech-sound block comes from the multi-resolution analysis property of the discrete wavelet transform, which is used to reduce the computational time for the pre-processing of speech recognition. The merging algorithm is proposed to extract vapid speech-sounds in terms of position and frequency range. It performs unvoiced/voiced classification and denoising. Since the merging algorithm can decide the processing parameters relating to voices only and is independent of system noises, it is useful for extracting valid speech-sounds. The merging algorithm has an adaptive feature for arbitrary system noises and an excellent denoising signal-to-noise ratio and a useful system tuning for the system implementation.

키워드

참고문헌

  1. Jin Ok Kim, Dae Joon Hwang, Han Wook Back, and Chin Hyun Chung, 'An application of the merging algorithm with the discrete transform to extract valid speech-sound,' in IEEE VIMS 2001, Budapest, Hungary, pp.67-70, IEEE, May, 2001 https://doi.org/10.1109/VIMS.2001.924903
  2. Raghuveer M. Rao and Ajit S. Bopardikar, Wavelet Transforms : Introduction to Theory and Applications, Addision Wesley, Readming, MA., 1998
  3. James S. Walker, A primer on Wavelets for Their Scientific Applications, CRC Press, Boca Ration, FL., 1999
  4. Randy Goldberg and Lance Riek, A Practical Handbook of Speech Coders, CRC Press, Boca Ratin, FL., 2000
  5. Jaideva C. Goswami and Andrew K. Chan, Fundamentals of Waveletsn : Theory, Algorithms and Applications, John Wiley & Sons, New York, 1999
  6. Anthony Teolis, Computational Signal Processing with Wavelets, Springer Verlag, New York, 1998
  7. C. Sidney Burrus, Ramesh A. Gopinath, and Hitao Guo, Introduction to Wavelets and Wavelet Transforms A primer, Prentice Hall, New Jersey, 1997
  8. T. L. Marzette, 'A new interpretation for capon's maximum likelihood method of frequency wavenumber spectral estimation,' IEEE Trans. Acoustics, Speech and Signal Processing, Vol.31, 1983 https://doi.org/10.1109/TASSP.1983.1164068
  9. John R. Deller, John H. L. Hansen, and John G. Proakis, Discrete-Time Processing of Speech Signals (IEEE press Classic Reissue), IEEE Press, New York, 2000
  10. D. L. Donoho, 'Denosing by soft-thresholding,' IEEE Trans. Information Theory, Vol.41, 1995 https://doi.org/10.1109/18.382009
  11. Agostino Abbate, Casimer M. Decusatis, and Pankej K. Das, Wavelets and Subband : Fundamentals and Applications, Birkhauser, Stuttgart, Germany, 2001
  12. R. Todd Ogden, Essential Wavelets for Statistical Applications and Data Analysis, Springer Verlag, New York, 1996
  13. Thomas W. Parsons, Voice and Speech Processing, McGraw-Hill, New York, 1986
  14. Sadaoki Furui, Digital Speech Processing, Synthesis and Recognition, Marcel Dekker, New York, 2nd edition, 2001
  15. Dan Jurasfky, James H. Martin, Keith Vander Linden, and Daniel Jurafsky, Speech and Language Processing : An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition, Prentice Hall, New Jersey, 2000
  16. Nelson Morgan and Ben Gold, Speech and Audio Signal Processing :　Processing and Perception of Speech and Music, John Wiley & Sons, New York, 1999
  17. Lawrence R. Rabiner and Ronald W. Schafer, Digital Processing of Speech Signals, Prentice Hall, New Jersey, 1978