Spectral Entropy Employment in Speech Enhancement based on Wavelet Packet

Authors: Talbi Mourad, Salhi Lotfi, Chérif Adnen

Abstract:

In this work, we are interested in developing a speech denoising tool by using a discrete wavelet packet transform (DWPT). This speech denoising tool will be employed for applications of recognition, coding and synthesis. For noise reduction, instead of applying the classical thresholding technique, some wavelet packet nodes are set to zero and the others are thresholded. To estimate the non stationary noise level, we employ the spectral entropy. A comparison of our proposed technique to classical denoising methods based on thresholding and spectral subtraction is made in order to evaluate our approach. The experimental implementation uses speech signals corrupted by two sorts of noise, white and Volvo noises. The obtained results from listening tests show that our proposed technique is better than spectral subtraction. The obtained results from SNR computation show the superiority of our technique when compared to the classical thresholding method using the modified hard thresholding function based on u-law algorithm.

Keywords: Enhancement, spectral subtraction, SNR, discrete wavelet packet transform, spectral entropy Histogram

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1057301

References:

[1] Y. Ephraim and D. Malah, "Speech enhancement using a minimum mean square error short time spectral amplitude estimator," IEEE Trans. On Acoust. Speech Signal Processing, vol. 32, no. 6, pp. 1109-1121, 1984.
[2] D.L. Donoho, "Denoising by soft thresholding," IEEE Trans on Information Theory, vol. 41, no. 3, pp. 613-627, 1995.
[3] I. M. Johnstone and B. W. Silverman, "Wavelet threshold estimators for data with correlated noise", J. Roy. Statist. Soc. B, vol. 59, pp. 319-351, 1997.
[4] X. Huang, A. Acero, H. Hon, "Spoken Language Processing," Prentice Hall, p. 474, 2001.
[5] Sungwook Chang, Y. Kwon, Sung-il Yang, and I-jae Kim. "Speech enhancement for non-stationary noise environment by adaptive wavelet packet" IEEE Tans. pp. 561-564, 2000.
[6] S.S. Chen, Basis Pursuit, Phd Thesis, Standford University, November 1995.
[7] D. Donoho and I. M. Johnstone. ÔÇÿÔÇÿIdeal spatial Adaptation via Wavelet Shrinkage-- Biometrika, 41. pp. 425-455, 1994.
[8] Waleed H. Abdulla. "HMM-based techniques for speech segments extraction". ISSN 1058-9244/02/S8.00 ┬® 2002-IOS Press.
[9] Mohammed BAHOURA and Jean ROUAT "Wavelet noise reduction: application to speech enhancement". CiteSeer, 2000.
[10] V. Balakrishnan, Nash Borges and Luke Parchment. "Wavelet denoising and speech enhancement," Spring 2006.
[11] H. Sheikhzadeh and H. Reza Abutalebi. ÔÇÿÔÇÿAn improved wavelet-based speech enhancement system--. Eurospeech, 2001.
[12] D. Donoho, I. M. Johnstone, G. Kerkyacharian et D.Picard. "Wavelet Shrinkage: Asymptotia" Journal of the Royel Statistical Society, Serie B,57, pp. 3019-3069, 1995.
[13] Jong Won Seok and Keun Sung Bae. "Speech enhancement with reduction of noise components in the wavelet domain," 0-8186-7919-0/97 S10.00 ┬® 1997 IEEE, pp. 1323-1326.
[14] Pham Van Tuan and Gernot Kubin ."DWT-Based classification of Acoustic-Phonetic Classes and Phonetic Units," International Conference on Spoken Language Processing (Interspeech-ICSLP) -2004.
[15] S. Mallat, A wavelet tour of signal processing. Academic Press, San Diego, USA (1998).
[16] E. Jafer, A.E.Mahdi, "Wavelet-based Voiced/Unvoiced classification algorithm", 4th EURASIP Conf., Vol.2, pp.667-672, Croatia,2003.