Speech enhancement for binaural hearing aids based on blind source separation

The availability of wireless technologies leads from monaural or bilateral hearing aids to binaural processing strategies. In this paper, we investigate a class of blind source separation (BSS)-based speech enhancement algorithms for binaural hearing aids. The blind binaural processing strategies are analyzed and evaluated for different scenarios, i.e., determined scenarios, where the number of sources does not exceed the number of available sensors and underdetermined scenarios, where there are more active source signals than microphones which is typical for hearing aid applications. These blind algorithms are an attractive alternative to beamforming as no a-priori knowledge on the sensor positions is required. Moreover, BSS algorithms have the advantage that their optimization criteria are solely based on the fundamental assumption of mutual statistical independence of the different source signals.

[1]  Walter Kellermann,et al.  A GENERALIZATION OF A CLASS OF BLIND SOURCE SEPARATION ALGORITHMS FOR CONVOLUTIVE MIXTURES , 2003 .

[2]  Walter Kellermann,et al.  Exploiting Narrowband Efficiency for Broadband Convolutive Blind Source Separation , 2007, EURASIP J. Adv. Signal Process..

[3]  Wolfgang Herbordt,et al.  Application of a double-talk resilient DFT domain adaptive filter for bin-wise stepsize controls to adaptive beamforming , 2005 .

[4]  Walter Kellermann,et al.  BSS for improved interference estimation for Blind speech signal Extraction with two microphones , 2009, 2009 3rd IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP).

[5]  Jacob Benesty,et al.  Audio Signal Processing for Next-Generation Multimedia Communication Systems , 2004 .

[6]  Walter Kellermann,et al.  A generalization of blind source separation algorithms for convolutive mixtures based on second-order statistics , 2005, IEEE Transactions on Speech and Audio Processing.

[7]  S. Godsill,et al.  Simple alternatives to the Ephraim and Malah suppression rule for speech enhancement , 2001, Proceedings of the 11th IEEE Signal Processing Workshop on Statistical Signal Processing (Cat. No.01TH8563).

[8]  R. McAulay,et al.  Speech enhancement using a soft-decision noise suppression filter , 1980 .

[9]  Shun-ichi Amari,et al.  Natural Gradient Works Efficiently in Learning , 1998, Neural Computation.

[10]  Walter Kellermann,et al.  Multi-Channel Source Separation Preserving Spatial Information , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[11]  Marc Moonen,et al.  Binaural Multi-Channel Wiener Filtering for Hearing Aids: Preserving Interaural Time and Level Differences , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[12]  Stefan Ernst,et al.  Combination of two-channel spectral subtraction and adaptive wiener post-filtering for noise reduction and dereverberation , 1996, 1996 8th European Signal Processing Conference (EUSIPCO 1996).

[13]  Marc Moonen,et al.  Binaural Noise Reduction Algorithms for Hearing Aids That Preserve Interaural Time Delay Cues , 2007, IEEE Transactions on Signal Processing.

[14]  Ephraim.  Speech enhancement using a minimum mean square error short-time spectral amplitude estimator , 1984 .

[15]  Christopher V. Alvino,et al.  Geometric source separation: merging convolutive source separation with geometric beamforming , 2001, Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584).

[16]  Peter Vary,et al.  Digital Speech Transmission: Enhancement, Coding and Error Concealment , 2006 .

[17]  Akihiko Sugiyama,et al.  A real time robust adaptive microphone array controlled by an SNR estimate , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[18]  Henning Puder.  Acoustic noise control: An overview of several methods based on applications in hearing aids , 1994, 2009 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing.

[19]  Christopher V. Alvino,et al.  Geometric source separation: merging convolutive source separation with geometric beamforming , 2001, Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop (IEEE Cat. No.01TH8584).

[20]  Walter Kellermann,et al.  Simultaneous localization of multiple sound sources using blind adaptive MIMO filtering , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[21]  Walter Kellermann,et al.  Blind Source Separation for Convolutive Mixtures: A Unified Treatment , 2004 .