AUTHORS: Héla Khazri, Mohamed Anouar Ben Messaoud, Aicha Bouzid

Download as PDF

ABSTRACT: In this paper, we propose an efficient multi-channel speech enhancement approach, based on the idea of adding a pre-treatment preceding the speech enhancement via a multi-channel method. This approach consists at first step in applying mono-channel speech enhancement method to process each noisy speech signal independently and then applying a multi-channel method based on the delay estimation and the blind Speech Separation in order to obtain the enhanced speech. Our idea is to apply a different class of mono-channel method in order to compare between them and to find the best combination that can remove a maximum noise without introducing artifacts. We resort the use of two classes of algorithms: the spectral subtraction and the statistical model based methods. In order to evaluate our proposed approach, we have compared it with our multi-channel speech enhancement method without a preprocessing. Our evaluation that was performed on a number of records corrupted by different types of noise like white, Car and babble shows that our proposed approach provides a higher noise reduction and a lower signal distortion.

KEYWORDS: Speech enhancement, Mono-channel Speech Separation, Multi-channel Speech Separation, Delay Estimation, Spectral Subtraction, Statistical Model Based Methods

REFERENCES:

[1] M.A. Ben Messaoud, A. Bouzid, and N. Ellouze, A New Biologically Inspired Fuzzy Expert System-Based Voiced/Unvoiced Decision Algorithm for Speech Enhancement. Cognitive computation. Vol. 8, No.1, pp.1-16, 2016.

[2] B.Xia and C.Bao , Wiener filtering based speech enhancement with Weighted Denoising Auto-encoder and noise classification, 2013.

[3] D.Cantzos, statistical enhancement methods for immersive audio environments and compressed audio, 2008.

[4] Kris Hermus, Patrick Wambacq, and Hugo Van hamme, A Review of Signal Subspace Speech Enhancement and Its Application to Noise Robust Speech Recognition, KatholiekeUniversiteit Leuven, 3001 LeuvenHeverlee, Belgium ,received 24 October 2005; revised 7 March 2006; Accepted 30 April 2006.

[5] L. J. Griffith and C. W. Jim, An alternative approach to linearly constrained adaptive beamforming, IEEE Trans. AntennasPropag, vol. 30, no. 1, pp. 27–34, Jan. 1982.

[6] Y. Kaneda and J. Ohga, Adaptive microphonearray system for noise reduction, IEEETrands. Acoust. Speech, Signal Process., pp.2109– 2112, 1986.

[7] H. F. Silverman and W. R. Pattterson, Visualizing the performance of large-aperture microphone arrays, in Proc. ICASSP’99, 1999, pp. 962–972.

[8] Saruwatari H. Saruwatari, T. Kawamura, T. Nishikawa, A. Lee, and K. Shikano, Blind source separation based on a fast-convergence algorithm combining ICA and beamforming, IEEE Trans. Speech Audio Process., vol. 14, no. 2, pp. 666–678, Mar. 2006.

[9] Y. Mori, H. Saruwatari, T. Takatani, S. Ukai, K. Shikano, T. Hiekata, Y. Ikeda, H. Hashimoto, and T. Morita, Blind separation of acoustic signals combining SIMO-modelbased independent component analysis and binary masking, EURASIP J. Appl. Signal Process., vol. 2006, 2006, article ID 34 970.

[10] P. Comon, Independent component analysis, a new concept? Signal Process,vol. 36, pp. 287– 314, 1994.

[11] Anuradha R. Fukane, Shashikant L. Sahare, Different Approaches of Spectral Subtraction method for Enhancing the Speech Signal in Noisy Environments,2011=11.

[12] Yang Lu, Philipos C. Loizou. A geometric approach to spectral subtraction, 2007. University of Texas-Dallas, Richardson, TX 75083-0688, United States Received 22 May 2007; received in revised form 18 January 2008; accepted 24 January 2008.

[13] Y. Ephraim and D. Malah.Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator, IEEE Trans. Acoust., Speech and Signal Processing, Vol. ASSP-32, No. 6, pp. 1109- 1121, 1984.

[14] Y. Ephraim and D. Malah.“Speech enhancement using a minimum mean square error short-time spectral amplitude estimator,” IEEE Trans. Acoust, Speech, Signal Process, vol. ASSP-32, no. 6, pp. 1109–1121, Dec 1984.

[15] Yang Lu, Philipos C. Loizou, Estimators of the Magnitude-Squared Spectrum and Methods for Incorporating SNR Uncertainty, 2011.

[16] Marc. Ferras.Font, Multi-Microphone Signal Processing For Automatics Speech Recognition in Meeting Rooms, 2005.

[17] A. Kareem, Z. Chao Zhu, Blind Source Separation Based of Brain Computer Interface System, 2014.

[18] Y.Zhang and W.H. Abdulla, A Comparative Study of Time-Delay Estimation Techniques Using Microphone Arrays,2005.The University of Auckland, Private Bag 92019, Auckland, New Zealand.

[19] C. H. Knapp and C. Carter, The generalized correlation method for estimation of time delay, IEEE Transactions on Acoustics, Speech and Signal Processing, vol. 24, August 1976.

[20] P. Aarabi and G. Shi, 'Phase-based dualmicrophone robust speech enhancement', IEEE Transactions on Systems, Man and Cybernetics, vol. 34, August 2004.

[21] C. Y. Lai and P. Aarabi, 'Multiple-microphone time-varying filters for robust speech recognition', Proc. ICASSP, 2004.

[22] A. Janin, J. Ang, S. Bhagat, R.Dhillon, J.Edwards, J. Macias-Guarasa, N. Morgan, B. Peskin, E. Shriberg, A. Stolcke, C. Wooters, and B. Wrede, The icsi meeting corpus: Resources and research, NIST ICASSP, Meeting Recognition Workshop (Montreal, Canada), May 2004.

[23] The NIST Meeting Room Project, http://www.nist.gov/speech/test beds/mrproj/

[24] Philipos C. Loizou and Y.Hu, “Evaluation of objective measures for speech enhancement, Proceedings of INTERSPEECH-2006, Philadelphia, PA, September 2006.

[25] M.A. Ben Messaoud, et A. Bouzid, Speech Enhancement Based on Wavelet Transform and Improved Subspace Decomposition. Journal of Audio Engineering society (JAES). Vol. 63, No.12, pp.1-11, 2015.

[26] Sandhya Hawaldar and Manasi Dixit. Speech Enhancement for Nonstationary Noise Environments. Signal & Image Processing: An International Journal, Vol. 2, No.4, 2011.

[27] Bolimera Ravi and T. Kishore Kumar. Speech Enhancement Using Kernel and Normalized Kernel Affine Projection Algorithm. Signal & Image Processing: An International Journal, Vol. 4, No.3, 2013.

[28] M.Ravichandra Kumar and B.RaviTeja. A Novel Uncertainty Parameter SR (Signal to Residual Spectrum Ratio) Evaluation Approach for Speech Enhancement. Signal & Image Processing: An International Journal, Vol. 4, No.3, 2013