A reproducing kernel Hilbert space approach for speech enhancement

The problem of speech enhancement has drawn a considerable amount of research attention over the past few years. Among the techniques developed one finds subspace methods, which seem to offer a good compromise between signal distortion and residual noise level. In this contribution, we present a novel subspace approach to single-channel speech enhancement. The eigen decomposition which was originally performed in the input space is now being done in a reproducing kernel Hilbert space, where the speech nonlinearities can be considered. The proposed algorithm was tested in various noise conditions including white, car, pink and train station noises at various signal-to-noise ratios (SNRs). Objective results show that for white noise, the algorithm presents an average improvement of 73.26% while for colored noise an average improvement of 68.42% is achieved. Subjective tests made on speech, corrupted with white and colored noises, demonstrate that the proposed algorithm provides a significant improvement over other speech enhancement methods found in literature.

[1]  Sanjit K. Mitra,et al.  Voice activity detection based on multiple statistical models , 2006, IEEE Transactions on Signal Processing.

[2]  Yariv Ephraim,et al.  A signal subspace approach for speech enhancement , 1995, IEEE Trans. Speech Audio Process..

[3]  Douglas D. O'Shaughnessy,et al.  Speech communication : human and machine , 1987 .

[4]  Rainer Martin,et al.  SPEECH ENHANCEMENT IN THE DFT DOMAIN USING LAPLACIAN SPEECH PRIORS , 2003 .

[5]  Rainer Martin,et al.  Speech enhancement using MMSE short time spectral estimation with gamma distributed speech priors , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  J. C. Rutledge,et al.  Noise reduction in hearing aids: a case for wavelet-based methods , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[7]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[8]  Yi Hu,et al.  A subspace approach for enhancing speech corrupted by colored noise , 2002, IEEE Signal Processing Letters.

[9]  Wei Li,et al.  Noise reduction and speech enhancement for high-quality wireless handsets , 2005, 14th Annual International Conference on Wireless and Optical Communications, 2005. WOCC 2005.

[10]  E. J. Diethorn.  A subband noise-reduction method for enhancing speech in telephony and teleconferencing , 1997, Proceedings of 1997 Workshop on Applications of Signal Processing to Audio and Acoustics.

[11]  Peter Vary,et al.  Speech Enhancement by MAP Spectral Amplitude Estimation Using a Super-Gaussian Speech Model , 2005, EURASIP J. Adv. Signal Process..

[12]  Yi Hu,et al.  A perceptually motivated approach for speech enhancement , 2003, IEEE Trans. Speech Audio Process..

[13]  Hanseok Ko,et al.  Speech enhancement for robust speech recognition in car environments using Griffiths-Jim ANC based on two-paired microphones , 2004, IEEE International Symposium on Consumer Electronics, 2004.

[14]  Louis L. Scharf,et al.  Multiwindow estimators of correlation , 1998, IEEE Trans. Signal Process..

[15]  Bin Chen,et al.  Speech enhancement using a MMSE short time spectral amplitude estimator with Laplacian speech modeling , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[16]  Soo Ngee Koh,et al.  Speech enhancement using 2-D Fourier transform , 2003, IEEE Trans. Speech Audio Process..

[17]  T. W. Anderson.  Asymptotically Efficient Estimation of Covariance Matrices with Linear Structure , 1973 .

[18]  D. Thomson,et al.  Spectrum estimation and harmonic analysis , 1982, Proceedings of the IEEE.

[19]  Benoît Champagne,et al.  Incorporating the human hearing properties in the signal subspace approach for speech enhancement , 2003, IEEE Trans. Speech Audio Process..

[20]  G. Faucon,et al.  A two-microphone approach for speech enhancement in hands-free communications , 1996, Proceedings of International Conference on Communication Technology. ICCT '96.

[21]  W. Bastiaan Kleijn,et al.  Improved Kalman filtering for speech enhancement , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..