A new efficient two-channel backward algorithm for speech intelligibility enhancement: A subband approach

Abstract This paper addresses the problem of speech intelligibility enhancement by adaptive filtering algorithms employed with subband techniques. The two structures named the forward and backward blind source separation structures are extensively used in the speech enhancement and source separation areas, and largely studied in the literature with convolutive and non-convolutive mixtures. These two structures use two-microphones to generate the convolutive/non-convolutive mixing signal, and provide at the outputs the target and the jammer signal components. In this paper, we focus our interest on the backward structure employed to enhance the speech signal from a convolutive mixture. Furthermore, we propose a subband implementation of this structure to improve its behavior with speech signal. The new proposed subband-Backward BSS (SBBSS) structure allows a very important improvement of the convergence speed of the adaptive filtering algorithms when the subband-number is selected high. In order to improve the robustness of the proposed subband structure, we have adapted then applied a new criterion that combines the System Mismatch and the Mean-Errors criterion minimization. The proposed subband backward structure, when it is combined with this new criterion minimization, allows to enhance the output speech signal by reducing the distortion and the noise components. The performance of the proposed subband backward structure is validated through several objective criteria which are given and described in this paper.

[1]  Dirk Van Compernolle,et al.  Feedforward and feedback in a symmetric adaptive noise canceler : “stability analysis in a simplified case” , 1992 .

[2]  Mohamed Djendi,et al.  Noise Cancellation using Two Closely Spaced Microphones: Experimental Study witha Specific Model and Two Adaptive Algorithms , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[3]  Meir Feder,et al.  Multi-channel signal separation by decorrelation , 1993, IEEE Trans. Speech Audio Process..

[4]  Dirk Van Compernolle,et al.  On the use of decorrelation in scalar signal separation , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[5]  T. Kailath,et al.  Fast, recursive-least-squares transversal filters for adaptive filtering , 1984 .

[6]  Kong-Aik Lee,et al.  Improving convergence of the NLMS algorithm using constrained subband updates , 2004, IEEE Signal Processing Letters.

[7]  Akihiko Sugiyama,et al.  An Adaptive Noise Canceller with Low Signal-Distortion Based on Variable Stepsize Subfilters for Human-Robot Communication , 2005, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[8]  Dirk Van Compernolle,et al.  Signal separation in a symmetric adaptive noise canceler by output decorrelation , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[9]  Mohamed Djendi,et al.  Improvement of the convergence speed and the tracking ability of the fast Newton type adaptive filtering (FNTF) algorithm , 2006, Signal Process..

[10]  Akihiko Sugiyama,et al.  An adaptive noise canceller with low signal distortion for speech codecs , 1999, IEEE Trans. Signal Process..

[11]  Kenji Nakayama,et al.  A Low-Distortion Noise Canceller and Its Learning Algorithm in Presence of Crosstalk , 2001 .

[12]  Joseph B. Evans,et al.  A new adaptive noise cancellation scheme in the presence of crosstalk (speech signals) , 1992 .

[13]  Woon-Seng Gan,et al.  Adaptive filtering using constrained subband updates , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[14]  Shoko Araki,et al.  Subband Based Blind Source Separation with Appropriate Processing for Each Frequency Band , 2003 .

[15]  Joseph B. Evans,et al.  Some experimental and theoretical results using a new adaptive filter structure for noise cancellation in the presence of crosstalk , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[16]  B. Widrow,et al.  Adaptive noise cancelling: Principles and applications , 1975 .

[17]  R. Merched,et al.  A delayless alias-free subband adaptive filter structure , 1997, Proceedings of 1997 IEEE International Symposium on Circuits and Systems. Circuits and Systems in the Information Age ISCAS '97.

[18]  Mohamed Djendi,et al.  Double pseudo affine projection algorithm for speech enhancement and acoustic noise reduction , 2012, 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO).

[19]  Martin Vetterli,et al.  Adaptive filtering in subbands with critical sampling: analysis, experiments, and application to acoustic echo cancellation , 1992, IEEE Trans. Signal Process..

[20]  Pierre Duhamel,et al.  Adaptive filtering in subbands using a weighted criterion , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[21]  Dirk Van Compernolle,et al.  Signal separation by symmetric adaptive decorrelation: stability, convergence, and uniqueness , 1995, IEEE Trans. Signal Process..

[22]  M. Gabrea.  Double affine projection algorithm-based speech enhancement algorithm , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[23]  Philipos C. Loizou,et al.  Subband-Based Blind Signal Processing for Source Separation in Convolutive Mixtures of Speech , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[24]  J. Dunlop,et al.  Improved adaptive noise cancellation in the presence of signal leakage on the noise reference channel , 1989 .

[25]  Mohamed Djendi,et al.  New frequency domain post-filters for noise cancellation using two closely spaced microphones , 2007, 2007 15th European Signal Processing Conference.

[26]  Pascal Scalart,et al.  Speech enhancement using harmonic regeneration , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[27]  V. U. Reddy,et al.  A new approach to subband adaptive filtering , 1999, IEEE Trans. Signal Process..

[28]  Woon-Seng Gan,et al.  Subband Adaptive Filtering: Theory and Implementation , 2009 .

[29]  Pascal Scalart,et al.  A two-step noise reduction technique , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[30]  Mariane R. Petraglia,et al.  A new delayless subband adaptive filter structure , 1999, IEEE Trans. Signal Process..

[31]  Sen M. Kuo,et al.  Principle and applications of asymmetric crosstalk-resistant adaptive noise canceler , 2000, J. Frankl. Inst..

[32]  Donald L. Duttweiler,et al.  Proportionate normalized least-mean-squares adaptation in echo cancelers , 2000, IEEE Trans. Speech Audio Process..

[33]  Roland Maas,et al.  A stereophonic acoustic signal extraction scheme for noisy and reverberant environments , 2013, Comput. Speech Lang..

[34]  Pascal Scalart,et al.  Improved Signal-to-Noise Ratio Estimation for Speech Enhancement , 2006, IEEE Transactions on Audio, Speech, and Language Processing.