The Journal of the Acoustical Society of Korea (한국음향학회지)

The Acoustical Society of Korea (한국음향학회)
권호 표지

A New Statistical Voice Activity Detector Based on UMP Test

UMP 테스트에 근거한 새로운 통계적 음성검출기

  • 장근원 (전남대학교 전자컴퓨터 공학부) ;
  • 장준혁 (인하대학교 전자전기 공학부) ;
  • 김동국 (전남대학교 전자컴퓨터 공학부)
  • Published : 2007.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

Voice activity detectors (VADs) are important in wireless communication and speech signal processing. In the conventional VAD methods. an expression for the likelihood ratio test (LRT) based on statistical models is derived. Then, speech or noise is decided by comparing the value of the expression with a threshold. We propose a new method with the modified decision rule based on the Gaussian distribution and the uniformly most power (UMP) test. This method requires the distribution of the absolute value of the incoming speech signal. Then we can obtain the final decision through the relation between the Rayleigh distributions. This VAD method can detect speech without a priori signal-to-noise ratio (SNR) which is required in the conventional VAD algorithms. Additionally, in the various VAD performance tests, the proposed VAD method is shown to be more effective than the traditional scheme.

음성검출기는 이동 통신이나 음성신호처리 등에 매우 중요한 기법으로 사용된다. 일반적인 음성검출방식은 통계적인 모델을 기반으로 하여 likelihood ratio test (LRT)를 하게 된다. 그리고 이 값을 임계값과 비교하여 음성인지 아닌지 판단하게 된다. 본 논문에서는 가우시안 (Gaussian) 분포를 기반으로 하고 uniformly most powerful (UMP) 테스트를 이용하여 새로운 음성검출기법을 제안한다. 새로운 음성검출기법의 결정규칙은 기존 LRT에 기반하여 UMP 테스트를 통해 식을 유도하였다. UMP 테스트를 이용하면, 입력음성에 대한 절대값의 확률 분포를 Rayleigh 분포 형태로 얻을 수 있으며, 이 분포에 따라 최종적으로 음성검출을 하게 된다. 이 새로운 방식의 음성검출기는 기존의 방식에서 필요한 a priori signal-to-noise ratio (SNR) 값을 구하지 않고도 음성 유무를 판단할 수 있다는 장점이 있다. 실제로 다양한 음성검출에 대한 성능 평가결과, 제안된 기법이 기존 방식에 비해 우수한 성능을 나타내었다.

Keywords

References

  1. A Dvis, S. Nordholm and R. Togneri, 'Statistical Voice Activity Detection Using Low-Variance Spectrum Estimation and an Adaptive Threshold,' IEEE Trans. Audio, Speech, and Language Processing, 14 (2) 412-424, March 2006 https://doi.org/10.1109/TSA.2005.855842
  2. J. S. Sohn, N. S. Kim and W. Y. Sung, 'A Statistical Model-Based Voice Activity Detection,' IEEE Signal Process, Lett., 6 (1) 1-3, 1999
  3. N. S. Kim, and J. -H. Chang, 'Spectral Enhancement Based on Global Soft Decision,' IEEE Signal Process. Lett.. 7 (5) 108-110, 2000 https://doi.org/10.1109/97.841154
  4. J. -H. Chang, J. W. Shin and N. S. Kim 'Voice Activity Detector Employing Generalized Gaussian Distribution,' IEEE Electronics Lett. 40 (24) 1561 - 1563, Nov. 2004 https://doi.org/10.1049/el:20047090
  5. Y. Ephraim and D. Malah, 'Speech Enhancement Using A Minimum Mean-square Error Short-time Spectral Amplitude Estimator'' IEEE Trans. Acoust., Speech, Signal Processing, Vol. ASSP-32, 1109-1121, Dec. 1984 https://doi.org/10.1109/TASSP.1984.1164453
  6. P. Vary and R. Martin. Digital Speech Transmission: Enhancement, Coding and Error Concealment, (John Wiley & Sons Inc., 2006)
  7. S. M. Kay Fundamentals of Statistical Signal Processing, (Volume 2: Detection Theory, Prentice Hall. 1998)
  8. J. -H. Chang and N. S. Kim, 'Voice Activity Detection Based on Complex Laplacian Model,' IEEE Electronics Lett., 39 (7) 632 - 634, April 2003 https://doi.org/10.1049/el:20030392
  9. J. -H. Chang, N. S. Kim and S. K. Mitra 'Voice Activity Detection Based on Multiple Statistical Models' IEEE Trans. Signal Processing, 54 (6) 1965 - 1976, June 2006 https://doi.org/10.1109/TSP.2006.874403
  10. R. Martin, 'Noise Power Spectral Density Estimation Based on Optimal Srroothinq and Minimum Statistics,' IEEE Trans. Speech and Audio Processing 9 (5) 504 - 512, Jul. 2001 https://doi.org/10.1109/89.928915
  11. Y. D. Cho and A Kondoz 'Analysis and Improvement of A Statistical Model-Based Voice Activity Detector,' IEEE Signal Processing, Lett. 8 (10) 27&-278, Oct. 2001
  12. A.Varga and H.J.M. Steeneken, 'Assessment for Automatic Speech Recognition: II.NOISEX-92: A Database and An Experiment to Study The Effect of Additive Noise on Speech Recognition Systems,' Speech Communication, 12 (3) 247-251, Ju1.1993 https://doi.org/10.1016/0167-6393(93)90095-3
  13. L. R. Rabiner and M. R. Sambur, 'Voiced-Unvoiced-Silence Detection Using Itakura LPC Distance Measure,' Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing. 2 323-326, May 1977