Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Speech Enhancement Algorithm Based on Teager Energy and Speech Absence Probability in Noisy Environments

잡음환경에서 Teager 에너지와 음성부재확률 기반의 음성향상 알고리즘

  • Park, Yun-Sik (Department of Electronic Engineering, Inha University) ;
  • An, Hong-Sub (Department of Electronic Engineering, Inha University) ;
  • Lee, Sang-Min (Department of Electronic Engineering, Inha University)
  • Received : 2011.08.09
  • Accepted : 2012.02.09
  • Published : 2012.05.25
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a novel speech enhancement algorithm for effective noise suppression in various noisy environments. In the proposed method, to result in improved decision performance for speech and noise segments, local speech absence probability (LSAP, local SAP) based on Teager energy of noisy speech is used as the feature parameter for voice activity detection (VAD) in each frequency subband instead of conventional LSAP. In addition, The presented method utilizes global SAP (GSAP) derived in each frame as the weighting parameter for the modification of the adopted TE operator to improve the performance of TE operator. Performances of the proposed algorithm are evaluated by objective test under various environments and better results compared with the conventional methods are obtained.

본 논문에서는 다양한 잡음환경에서 효과적인 잡음 제거 (NS, noise suppression)를 위한 새로운 음성향상 (speech enhancement) 알고리즘을 제안한다. 제안된 방법에서는 음성향상 알고리즘에서 잡음전력 갱신을 위한 음성검출 (VAD, voice activity detection)의 피쳐 (feature) 파라미터로서 오염된 음성신호를 기반으로 주파수 밴드 별로 도출되는 기존의 지역 음성부재확률 (LSAP, local speech absecne probability) 대신 오염된 음성신호의 Teager energy (TE)를 적용한 LSAP를 적용한다. 또한 적용된 TE operator의 성능을 개선하기 위하여 프레임 단위로 도출되는 전역 음성부재확률 (GSAP, global SAP)을 TE의 가중치 파라미터로서 적용한다. 제안된 알고리즘은 기존의 방법과 객관적인 실험을 통해 비교 평가한 결과 다양한 배경잡음 환경에서 향상된 성능을 보였다.

Keywords

References

  1. Y. Ephraim and D. Malah, "Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator," IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-32, no. 6, pp. 1109-1121, Dec. 1984.
  2. 박윤식, 조규행, 장준혁, "복소 라플라시안 확률 밀도 함수에 기반한 음성 향상 기법," 전자공학회논문지, 제44권, SP편 제6호, 111-117쪽, 2007. 11월.
  3. L. Karray, C. Mokbel and J. Monne, "Solutions for robust. speech/non-speech detection in wireless environment," presented at the IVTTA, Sep. 1988.
  4. F. Jabloun, A. E. Cetin and E. Erzin, "Teager energy based feature parameters for speech recognition in car noise," IEEE Signal Processing Letters, vol. 6, pp. 259-261, 1999. https://doi.org/10.1109/97.789604
  5. K. C. Wang and Y. H. Tsai, "Voice activity detection algorithm with low signal-to-noise ratios based on spectrum entropy," Second International Symposium on Universal Communication 2008, pp. 423-428, Dec. 2008.
  6. J. Sohn, W. Sung, "A voice activity detector employing soft decision based noise spectrum adaptation," in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing, pp. 365-368, 1998.
  7. N. S. Kim and J.-H. Chang, "Spectral enhancement based on global soft decision," IEEE Signal Processing Letters, vol. 7, no. 5, pp. 108-110, May 2000. https://doi.org/10.1109/97.841154
  8. J. -H. Chang and N. S. Kim, "Speech enhancement : new approaches to soft decision," IEICE Trans. Inf. and Syst., VolE84-D, No.9, pp 1231-1240, Sep. 2001.
  9. 조규행, 박윤식, 장준혁, "Smoothed global soft decision에 근거한 음성 향상 기법," 전자공학회논문지, 제44권, SP편 제6호, 118-123쪽, 2007년 11월.
  10. 박윤식, 이상민, "잡음환경에서 Teager Energy 기반의 전역 음성부재확률을 이용하는 음성검출," 전자공학회논문지, 제49권, SP편 제1호.
  11. Yi Hu and P. C. Loizou, "Evaluation of objective quality mea-sures for speech enhancement," IEEE Trans. ASLP, vol. 16, pp. 229-238, Jan. 2008.