A spectral filtering method based on hybrid wiener filters for speech enhancement

It is well known that speech enhancement using spectral filtering will result in residual noise. Residual noise which is musical in nature is very annoying to human listeners. Many speech enhancement approaches assume that the transform coefficients are independent of one another and can thus be attenuated separately, thereby ignoring the correlations that exist between different time frames and within each frame. This paper, proposes a single channel speech enhancement system which exploits such correlations between the different time frames to further reduce residual noise. Unlike other 2D speech enhancement techniques which apply a post-processor after some classical algorithms such as spectral subtraction, the proposed approach uses a hybrid Wiener spectrogram filter (HWSF) for effective noise reduction, followed by a multi-blade post-processor which exploits the 2D features of the spectrogram to preserve the speech quality and to further reduce the residual noise. This results in pleasant sounding speech for human listeners. Spectrogram comparisons show that in the proposed scheme, musical noise is significantly reduced. The effectiveness of the proposed algorithm is further confirmed through objective assessments and informal subjective listening tests.

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

[2]  G. Whipple Low residual noise speech enhancement utilizing time-frequency filtering , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[3]  John H. L. Hansen,et al.  Speech enhancement using a constrained iterative sinusoidal model , 2001, IEEE Trans. Speech Audio Process..

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

[5]  Yi Hu,et al.  Evaluation of objective measures for speech enhancement , 2006, INTERSPEECH.

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

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

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

[9]  Soo Ngee Koh,et al.  Improved noise suppression filter using self-adaptive estimator of probability of speech absence , 1999, Signal Process..

[10]  Douglas D. O'Shaughnessy,et al.  Speech enhancement based conceptually on auditory evidence , 1991, IEEE Trans. Signal Process..

[11]  Kah-Chye Tan,et al.  Postprocessing method for suppressing musical noise generated by spectral subtraction , 1998, IEEE Trans. Speech Audio Process..

[12]  Andrew Sekey,et al.  An Objective Measure for Predicting Subjective Quality of Speech Coders , 1992, IEEE J. Sel. Areas Commun..

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

[14]  John S. D. Mason,et al.  Noise Compensation using Spectrogram Morphological Filtering , 2002 .

[15]  Thomas Quatieri,et al.  Discrete-Time Speech Signal Processing: Principles and Practice , 2001 .

[16]  R. Goubran,et al.  Musical noise reduction in speech using two-dimensional spectrogram enhancement , 2003, The 2nd IEEE Internatioal Workshop on Haptic, Audio and Visual Environments and Their Applications, 2003. HAVE 2003. Proceedings..