Improving Speech Intelligibility in Binaural Hearing Aids by Estimating a Time-Frequency Mask with a Weighted Least Squares Classifier

An efficient algorithm for speech enhancement in binaural hearing aids is proposed. The algorithm is based on the estimation of a time-frequency mask using supervised machine learning. The standard least-squares linear classifier is reformulated to optimize a metric related to speech/noise separation. The method is energy-efficient in two ways: the computational complexity is limited and the wireless data transmission optimized. The ability of the algorithm to enhance speech contaminated with different types of noise and low SNR has been evaluated. Objective measures of speech intelligibility and speech quality demonstrate that the algorithm increments both the hearing comfort and speech understanding of the user. These results are supported by subjective listening tests.

[1]  Yi Jiang,et al.  Binaural Classification for Reverberant Speech Segregation Using Deep Neural Networks , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[2]  Martin Vetterli,et al.  Rate-Constrained Beamforming for Collaborating Hearing Aids , 2006, 2006 IEEE International Symposium on Information Theory.

[3]  Manuel Rosa-Zurera,et al.  A machine learning approach for computationally and energy efficient speech enhancement in binaural hearing aids , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  DeLiang Wang,et al.  On the optimality of ideal binary time-frequency masks , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[5]  Tao Zhang,et al.  DNN-based enhancement of noisy and reverberant speech , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Scott Rickard,et al.  Blind separation of speech mixtures via time-frequency masking , 2004, IEEE Transactions on Signal Processing.

[7]  James M. Kates,et al.  Digital hearing aids. , 2008, Harvard health letter.

[8]  Jesper Jensen,et al.  An Algorithm for Intelligibility Prediction of Time–Frequency Weighted Noisy Speech , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[9]  Philipos C. Loizou,et al.  Reasons why Current Speech-Enhancement Algorithms do not Improve Speech Intelligibility and Suggested Solutions , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[10]  Takeaki Kariya,et al.  Generalized Least Squares , 2004 .

[11]  Teresa Cervera,et al.  Test of Spanish sentences to measure speech intelligibility in noise conditions , 2011, Behavior research methods.

[12]  Henry Cox,et al.  Robust adaptive beamforming , 2005, IEEE Trans. Acoust. Speech Signal Process..

[13]  Manuel Rosa-Zurera,et al.  Rate-constrained source separation for speech enhancement in wireless-communicated binaural hearing aids , 2013, EURASIP J. Adv. Signal Process..

[14]  Marc Moonen,et al.  Comparison of Reduced-Bandwidth MWF-Based Noise Reduction Algorithms for Binaural Hearing Aids , 2007, 2007 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.

[15]  Jun Du,et al.  An Experimental Study on Speech Enhancement Based on Deep Neural Networks , 2014, IEEE Signal Processing Letters.

[16]  Sriram Srinivasan,et al.  Rate-Constrained Beamforming in Binaural Hearing Aids , 2009, EURASIP J. Adv. Signal Process..

[17]  DeLiang Wang,et al.  Monaural speech segregation based on pitch tracking and amplitude modulation , 2002, IEEE Transactions on Neural Networks.