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

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

Sound Reinforcement Based on Context Awareness for Hearing Impaired

청각장애인을 위한 상황인지기반의 음향강화기술

  • Choi, Jae-Hun (Department of Electronics Engineering, Inha University) ;
  • Chang, Joon-Hyuk (Department of Electronic Engineering, Hanyang University)
  • 최재훈 (인하대학교 전자공학부) ;
  • 장준혁 (한양대학교 융합전자공학부)
  • Received : 2011.01.18
  • Accepted : 2011.05.11
  • Published : 2011.09.25
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we apply a context awareness based on Gaussian mixture model (GMM) to a sound reinforcement for hearing impaired. In our approach, the harmful sound amplified through the sound reinforcement algorithm according to context awareness based on GMM which is constructed as Mel-frequency cepstral coefficients (MFCC) feature vector from sound data. According to the experimental results, the proposed approach is found to be effective in the various acoustic environments.

본 논문에서는 청각장애인을 위한 음향 데이터를 이용한 음향강화 알고리즘을 Gaussian Mixture Model (GMM)을 이용한 상황인지 시스템 기반으로 제안한다. 음향 신호 데이터에서 Mel-Frequency Cepstral Coefficients (MFCC) 특징벡터를 추출하여 GMM을 구성하고 이를 기반으로 상황인지 결과에 따라 위험음향일 경우 음향강화기술을 제안한다. 실험결과 제안된 상황인지 기반의 음향강화 알고리즘이 다양한 음향학적 환경에서 우수한 성능을 보인 것을 알 수 있었다.

Keywords

References

  1. 김종태, 신석철, 원용명, 이상철, 김원우, "청각 및 언어장애인용 유선통신 대화장치 및 보조기기 개발", 정보통신연구진흥원, [IITA] 정보통신연구진흥원 학술기사
  2. L. Ma, B. P. Milner and D. Smith, "Acoustic environment classification," ACM Transactions on Speech and Language Processing, Vol.3, No.2, Jul. 2006, pp. 1-22.
  3. Y. Toyoda, J. Huang, S. Ding and Y. Liu, "Environmental sound recognition by multilayered neural networks," in Proc. International Conference on Computer and Information Technology, Sep. 2004, pp. 123-127.
  4. L. Couvreur and M. Laniray, "Automatic noise recognition in urban environments based on artificial neural networks and hidden Markov models," InterNoise, Prague, Czech Republic, Aug. 2004.
  5. N. Sawhney, "Situational awareness from environmental sounds," MIT Media Lab. Technical Report, June 1997.
  6. S. Sigurdsson, K. B. Petersen, and T. Lehn-Schioler, "Mel Frequency Cepstral Coefficients: An evaluation of Robustness of MP3 Encoded Music," in Proc. Int. Conf. Music Inf. Retrieval, pp. 286-289, 2005.
  7. C. M. Bishop, Neural networks for pattern recognition, Oxford University Press, UK, 1995.
  8. R. O. Duda, P. E. Hart and D. G. Stork, Pattern classification, John Wiley & Sons, INC., 2001.
  9. G. Xuan, W. Zhang and P. Chai, "EM algorithms of Gaussian mixture model and hidden Markov model,'' in Proc. International Conference on Image Processing, Vol. 1, Oct. 2001, pp. 145-148.
  10. J. A. Bilmes, "A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixed and hidden Markov Models," International Computer Science Institute, Technical Report, TR-97-02, Apr. 1998.
  11. A. P. Dempster, N. M. Land and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," Journal of the Royal Statistical Society, Series B, Vol. 39, No. 1, 1977, pp. 1-38.
  12. J. W. Shin, N. S. Kim, W. Sung, "A statistical model-based voice activity detection," IEEE Signal Processing Letters, vol. 6 no. 1, pp. 1-3, Jan. 1999.