Evaluating solutions to noise reduction for speech using Wavelet transformations

##plugins.themes.academic_pro.article.main##

Author

  • Duong Ngoc Phap, Vo Thi Dieu Hanh

Keywords:

Wavelet
PSWF
noise reduction
speech
Wavelet domain

Abstract

The article focuses on demonstrating noise reduction techniques for enhancing speech signaling using transformations in the wavelet domain. Noise determination with Percentile Filter is used to perform preprocessing for interference suppression techniques including hard-edge interference compression, soft-band interference compression, and noise correction using sensory wavelet filtering (PSWF). The simulation will show the results of the noise reduction of the three above methods in different noise environments, and will also make comparisons with the noise reduction methods in the research frequency domain The results show that the techniques in the wavelet domain for noise reduction are good, especially for color noise.

References

    [1] Phạm Văn Tuấn, Hoàng Lê Uyên Thục, “Giải pháp giảm nhiễu trong miền Wavelet để nâng cao hiệu suất nhận dạng tiếng nói tự động”, Tạp chí Khoa học và Công nghệ, Đại học Đà Nẵng, số 4(39), 2010.
    [2] Boll, S.F., “Suppression of acoustic noise in speech using spectral subtraction”, IEEE Trans, Acoust. Speech Signal Process., 27(2), 113-120, 1979.
    [3] Ephraim, Yariv, and David Malah, Speech enhancement using optimal non-linear spectral amplitude estimation, Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP'83, Vol. 8, IEEE, 1983.
    [4] Cohen, Israel, “Speech enhancement using a noncausal a priori SNR estimator”, IEEE signal processing letters, 11.9 (2004): 725-728.
    [5] Graps, Amara, “An introduction to Wavelets”, IEEE computational science and engineering, 2.2 (1995): 50-61.
    [6] Pham T.V., Gernot Kubin, “WPD-based Noise Suppression Using Nonlinearly Weighted Threshold Quantile Estimation and Optimal Wavelet Shrinking”, Proc. Interspeech, Lisboa, Portugal, 4-8 Sep., 2005.
    [7] Van Pham, Tuan, Wavelet Analysis For Robust Speech Processing and Applications, Diss. Ph. D. Thesis, 2007.
    [8] Donohol, M. Johnstone, and M. Johnsone, Ideal spatial adaptation via Wavelet shrinkage, Biometrika 12.8 (1994): 430-445.
    [9] Donoho D. L., “De-noising by soft thresholding”, IEEE Trans. Information Theory, 41:613–627, 1995.
    [10] Pham T.V., Gernot Kubin, Erhard Rank, Robust Speech Recognition Using Adaptive Noise Threshold Estimation And Wavelet Shrinkage, Proc. IEEE ICCE, Hoi An, Vietnam, 04-06 Feb., 2008.
    [11] Ephraim Y. and D. Malah, “Speech enhancement using a minimum mean square error log-spectral amplitude estimator”, IEEE Transactions on Acoustics, Speech, and Signal Processing, 33:443–445, 1985.
    [12] Ephraim, Yariv, and David Malah, “Speech enhancement using a minimum mean-square error log-spectral amplitude estimator”, IEEE Transactions on Acoustics, Speech and Signal Processing, 33.2 (1985): 443-445.
    [13] http://ecs.utdallas.edu/loizou/speech/noizeus/ truy cập lần cuối 20/03/2017.
Read more

##plugins.themes.academic_pro.article.sidebar##

Published

May 31, 2017
Download
PDF (Tiếng Việt)
How to Cite
Duong Ngoc Phap, Vo Thi Dieu Hanh. “Evaluating Solutions to Noise Reduction for Speech Using Wavelet Transformations”. The University of Danang - Journal of Science and Technology, vol. 5, no. 114, May 2017, pp. 1-5, https://jst-ud.vn/jst-ud/article/view/3295.

##plugins.themes.academic_pro.article.details##