PARAMETER SETTING OF NOISE REDUCTION FILTER USING SPEECH RECOGNITION SYSTEM

Tomomi Abe, Mitsuharu Matsumoto, Shuji Hashimoto

2010

Abstract

This paper describes parameter setting of noise reduction filter using speech recognition system. Parameter setting problem is usually solved by maximization or minimization of some objective evaluation functions such as correlation and statistical independence. However, when we consider a single-channel noisy signal, it is difficult to employ such objective functions. It is also difficult to employ them when we consider impulsive noise because its duration is very small to use this assumption. To solve the problems, we directly use a speech recognition system as evaluation function for parameter setting. As an example, we employ time-frequency e-filter and Julius as a filtering system and a speech recognition system, respectively. The experimental results show that the proposed approach has a potential to set the parameter in unknown environments.

References

  1. Abe, T., Matsumoto, M., and Hashimoto, S. (2007). Noise reduction combining time-domain e -filter and timefrequency e -filter. In J. of the Acoust. Soc. America., volume 122, pages 2697-2705.
  2. Abe, T., Matsumoto, M., and Hashimoto, S. (2009). Parameter optimization in time-frequency e -filter based on correlation coefficient. In Proc. of SIGMAP2009.
  3. Harashima, H., Odajima, K., Shishikui, Y., and Miyakawa, H. (1982). e -separating nonlinear digital filter and its applications. In IEICE trans on Fundamentals., volume J65-A, pages 297-303.
  4. Kawahara, T., Lee, A., Kobayashi, T., Takeda, K., Minematsu, N., Sagayama, S., Itou, K., Ito, A., Yamamoto, M., Yamada, A., Utsuro, T., and Shikano, K. (2000). Free software toolkit for japanese large vocabulary continuous speech recognition. In Proc. of ICSLP 2000.
  5. Lee, A. and Kawahara, T. (2009). Recent development of open-source speech recognition engine julius. In Proc. of APSIPA-ASC 2009.
  6. Lee, A., Kawahara, T., and Shikano, K. (2001). Julius - an open source real-time large vocabulary recognition engine. In Proc. of EUSIPCO2001., pages 1691- 1694.
  7. Lim, J. S., Oppenheim, A. V., and Braida, L. (1978). Evaluation of an adaptive comb filtering method for enhancing speech degraded by white noise addition. In IEEE Trans. on Acoust. Speech Signal Process., volume ASSP-26, pages 419-423.
  8. Matsumoto, M. and Hashimoto, S. (2009). Estimation of optimal parameter in e -filter based on signal-noise decorrelation. In IEICE Trans. on Information and Systems, volume E92-D, pages 1312-1315.
  9. Mrazek and Navara, M. (2003). Selection of optimal stopping time for nonlinear diffusion filtering. In Int'l Journal of Computer Vision, volume 52, pages 189- 203.
  10. Sporring, J. and Weickert, J. (1999). Information measures in scale-spaces. In IEEE Transs on Information Theory, volume 45, pages 1051-1058.
  11. Umeda, S. (2000). Blind deconvolution of blurred images by using ica. In IEICE Trans. on Fundamentals, volume J83-A, pages 677-685.
Download


Paper Citation


in Harvard Style

Abe T., Matsumoto M. and Hashimoto S. (2010). PARAMETER SETTING OF NOISE REDUCTION FILTER USING SPEECH RECOGNITION SYSTEM . In Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation - Volume 1: ICNC, (IJCCI 2010) ISBN 978-989-8425-32-4, pages 387-391. DOI: 10.5220/0003054903870391


in Bibtex Style

@conference{icnc10,
author={Tomomi Abe and Mitsuharu Matsumoto and Shuji Hashimoto},
title={PARAMETER SETTING OF NOISE REDUCTION FILTER USING SPEECH RECOGNITION SYSTEM},
booktitle={Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation - Volume 1: ICNC, (IJCCI 2010)},
year={2010},
pages={387-391},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003054903870391},
isbn={978-989-8425-32-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation - Volume 1: ICNC, (IJCCI 2010)
TI - PARAMETER SETTING OF NOISE REDUCTION FILTER USING SPEECH RECOGNITION SYSTEM
SN - 978-989-8425-32-4
AU - Abe T.
AU - Matsumoto M.
AU - Hashimoto S.
PY - 2010
SP - 387
EP - 391
DO - 10.5220/0003054903870391