한국통신학회논문지 (The Journal of Korean Institute of Communications and Information Sciences)

  • 제40권5호
  • /
  • Pages.924-930
  • /
  • 2015
  • /
  • 1226-4717(pISSN)
  • /
  • 2287-3880(eISSN)
한국통신학회 (The Korean Institute of Commucations and Information Sciences)
권호 표지
DOI QR코드

DOI QR Code

음성 검출 기반의 저연산 이득 제어 알고리즘

A Gain Control Algorithm of Low Computational Complexity based on Voice Activity Detection

  • Kim, Sang-Kuyn (Inha University Division of Electronic Engineering) ;
  • Cho, Woo-Hyeong (Inha University Division of Electronic Engineering) ;
  • Jeong, Min-A (Mokpo National University Department of Computer Engineering) ;
  • Kwon, Jang-Woo (Inha University Division of Computer Engneering and Information) ;
  • Lee, Sangmin (Inha University Division of Electronic Engineering)
  • 투고 : 2015.04.02
  • 심사 : 2015.05.14
  • 발행 : 2015.05.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 잡음 환경에서 적은 연산량으로 소형 음향기기의 음질 향상을 위한 새로운 저연산 이득 제어 알고리즘을 제안한다. 대표적인 소형 음향기기인 보청기의 이득 제어 알고리즘은 입력 신호를 잡음 제거 한 후 이 신호의 파워를 기준으로 광역동범위압축 (wide dynamic range compression, WDRC)을 하기 때문에 불필요한 신호까지 증폭된다. 제안된 이득 제어 알고리즘은 음성 검출기 (voice activity detection, VAD)의 결과를 이용하여 음성의 존재 유/무에 따라 적응적으로 이득을 제어한다. 성능 평가를 위해 제안된 알고리즘은 VAD를 적용하지 않은 알고리즘과 정상 및 비정상 잡음환경에서 다양한 조건을 부과하여 비교하였으며, 실험결과 제안된 알고리즘이 전체 성능 및 잡음 구간에서 향상된 결과를 보였다.

In this paper, we propose a novel approach of low computational complexity to improve the speech quality of the small acoustic equipment in noisy environment. The conventional gain control algorithm suppresses the noise of input signal, and then the part of wide dynamic range compression (WDRC) amplifies the undesired signal. The proposed algorithm controls the gain of hearing aids according to speech present probability by using the output of a voice activity detection (VAD). The performance of the proposed scheme is evaluated under various noise conditions by using objective measurement and yields superior results compared with the conventional algorithm.

키워드

참고문헌

  1. B. Edwards, "The future of hearing aid technology," Trends in Amplification, vol. 11, no. 1, pp. 31-46, Mar. 2007. https://doi.org/10.1177/1084713806298004
  2. H. M. Yoon and H. W. Lee, "A new adaptive algorithm for the acoustic echo canceller," J. Commun. Networks (JCN), vol. 26, no. 6, pp. 77-81, Jun. 2001.
  3. C. M. Lee, S. H. Bae, J. H. Kim, and N. S. Kim, "Spectro-temporal filtering based on soft decision for stereophonic acoustic echo suppression," J. Commun. Networks (JCN), vol. 39C, no. 12, pp. 1346-1351, Nov. 2014.
  4. S. M. Kuo and D. R. Morgan, "Noise reduction by using eigenfilter in cyclic prefix system based on SNR," J. Commun. Networks (JCN), vol. 39B, no. 10, pp. 700-707, Oct. 2014.
  5. J. G. Kim, "A multichannel compression strategy for a digital hearing Aid," in Proc. ICASSP-97, Munich, Germany, pp. 411-415, 1997.
  6. S. B. Moon, Y. B. Chae, and S. H. Jun, "Optimal feature parameters extraction for speech recognition of ship's wheel orders," J. the Korean Soc. Marine Environment & Safety, vol. 13, no. 2, pp. 161-167, 2007.
  7. J. Sohn, N. S. Kim, and W. Sung, "A statistical model-based voice activity detection," IEEE Signal Processing Lett., vol. 6, no. 1, pp. 1-3, Jan. 1999. https://doi.org/10.1109/97.736233
  8. Y. Ephraim and D. Malah, "Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator," IEEE Trans. Acoustics, Speech and Signal Processing, vol. ASSP-32, no. 6, pp. 1190-1121, Dec. 1984.
  9. Y. S. Park and S. Lee, "Voice activity detection using global speech absence probability based on teager energy for speech enhancement," IEICE Trans. Inf. and Syst., vol. E95-D, no. 10, pp. 2568-2571, Oct. 2012. https://doi.org/10.1587/transinf.E95.D.2568
  10. Y. Hu and P. C. Loizou, "Evaluation of objective quality measures for speech enhancement," IEEE Trans. Audio Speech Lang. Process., vol. 16, no. 1, pp. 229-238, Jan. 2008. https://doi.org/10.1109/TASL.2007.911054