Weak speech recovery for single-channel speech enhancement

Numerous speech enhancement strategies have been proposed to counteract the background noise present in communication and thus improve speech quality. However, such an improvement does not imply an improvement in speech intelligibility. Therefore, the issue become challenging especially it concerns single-channel situations. In this study, we present an approach to improve both speech quality and intelligibility, that is to recover weak speech. Here, weak speech is determined based on the pitch estimation and signal to noise ratio (SNR). With both parameters, we review the methodology of spectral subtraction and pitch estimation and then explore the possibility of improving the speech by incorporating the pitch information.

[1]  Sven Nordholm,et al.  Adaptive microphone array with noise statistics updates , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[2]  P. Boersma.  ACCURATE SHORT-TERM ANALYSIS OF THE FUNDAMENTAL FREQUENCY AND THE HARMONICS-TO-NOISE RATIO OF A SAMPLED SOUND , 1993 .

[3]  H. T. Hu.  Comb filtering of noisy speech using overlap-and-add approach , 1998 .

[4]  Ing Yann Soon,et al.  Over-Attenuated Components Regeneration for Speech Enhancement , 2010, IEEE Transactions on Audio, Speech, and Language Processing.

[5]  I. Cohen,et al.  Noise estimation by minima controlled recursive averaging for robust speech enhancement , 2002, IEEE Signal Processing Letters.

[6]  Richard M. Schwartz,et al.  Enhancement of speech corrupted by acoustic noise , 1979, ICASSP.

[7]  Nils Westerlund,et al.  Counteracting Acoustic Disturbances in Human Speech Communication , 2006 .

[8]  Jérôme Boudy,et al.  Experiments with a nonlinear spectral subtractor (NSS), Hidden Markov models and the projection, for robust speech recognition in cars , 1991, Speech Commun..

[9]  Soo Ngee Koh,et al.  A post-processing technique for regeneration of over-attenuated speech , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[10]  Rainer Martin,et al.  Spectral Subtraction Based on Minimum Statistics , 2001 .

[11]  S. Boll,et al.  Suppression of acoustic noise in speech using spectral subtraction , 1979 .

[12]  David Malah,et al.  Speech enhancement using a minimum mean-square error log-spectral amplitude estimator , 1984, IEEE Trans. Acoust. Speech Signal Process..

[13]  Mattias Dahl,et al.  Speech Enhancement using an Adaptive Gain Equalizer , 2003 .

[14]  Sven Nordholm,et al.  A subband space constrained beamformer incorporating voice activity detection [speech enhancement applications] , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[15]  A.V. Oppenheim,et al.  Enhancement and bandwidth compression of noisy speech , 1979, Proceedings of the IEEE.

[16]  Olivier Cappé,et al.  Elimination of the musical noise phenomenon with the Ephraim and Malah noise suppressor , 1994, IEEE Trans. Speech Audio Process..

[17]  Peter Jax,et al.  A novel psychoacoustically motivated audio enhancement algorithm preserving background noise characteristics , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[18]  Philipos C. Loizou,et al.  A multi-band spectral subtraction method for enhancing speech corrupted by colored noise , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[19]  Nathalie Virag,et al.  Single channel speech enhancement based on masking properties of the human auditory system , 1999, IEEE Trans. Speech Audio Process..

[20]  Ronald E. Crochiere,et al.  A weighted overlap-add method of short-time Fourier analysis/Synthesis , 1980 .

[21]  Philipos C. Loizou,et al.  Speech Enhancement: Theory and Practice , 2007 .

[22]  Sridha Sridharan,et al.  Speech enhancement using critical band spectral subtraction , 1998, ICSLP.