Speech Enhancement, Gain, and Noise Spectrum Adaptation Using Approximate Bayesian Estimation

This paper presents a new approximate Bayesian estimator for enhancing a noisy speech signal. The speech model is assumed to be a Gaussian mixture model (GMM) in the log-spectral domain. This is in contrast to most current models in frequency domain. Exact signal estimation is a computationally intractable problem. We derive three approximations to enhance the efficiency of signal estimation. The Gaussian approximation transforms the log-spectral domain GMM into the frequency domain using minimal Kullback-Leiber (KL)-divergency criterion. The frequency domain Laplace method computes the maximum a posteriori (MAP) estimator for the spectral amplitude. Correspondingly, the log-spectral domain Laplace method computes the MAP estimator for the log-spectral amplitude. Further, the gain and noise spectrum adaptation are implemented using the expectation-maximization (EM) algorithm within the GMM under Gaussian approximation. The proposed algorithms are evaluated by applying them to enhance the speeches corrupted by the speech-shaped noise (SSN). The experimental results demonstrate that the proposed algorithms offer improved signal-to-noise ratio, lower word recognition error rate, and less spectral distortion.

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

[2]  Ho-Young Jung,et al.  Speech Coding And Noise Reduction Using Ica-Based Speech Features , 2000 .

[3]  Rainer Martin,et al.  Speech enhancement based on minimum mean-square error estimation and supergaussian priors , 2005, IEEE Transactions on Speech and Audio Processing.

[4]  Rainer Martin,et al.  MMSE estimation of magnitude-squared DFT coefficients with superGaussian priors , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[5]  Jae S. Lim,et al.  The unimportance of phase in speech enhancement , 1982 .

[6]  Yariv Ephraim,et al.  Recent Advancements in Speech Enhancement , 2004 .

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

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

[9]  John R. Hershey,et al.  Monaural speech separation and recognition challenge , 2010, Comput. Speech Lang..

[10]  Ross D. Shachter,et al.  Laplace's Method Approximations for Probabilistic Inference in Belief Networks with Continuous Variables , 1994, UAI.

[11]  CohenIsrael,et al.  An integrated real-time beamforming and postfiltering system for nonstationary noise environments , 2003 .

[12]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[13]  Christophe Beaugeant,et al.  SPEECH ENHANCEMENT USING A MINIMUM LEAST SQUARE AMPLITUDE ESTIMATOR , 2001 .

[14]  Simon J. Godsill,et al.  Towards a perceptually optimal spectral amplitude estimator for audio signal enhancement , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[15]  Michael S. Brandstein.  On the use of explicit speech modeling in microphone array applications , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[16]  Wai-Kai Chen,et al.  The Electrical Engineering Handbook , 2004 .

[17]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[18]  T. Lotter.  NOISE REDUCTION BY MAXIMUM A POSTERIORI SPECTRAL AMPLITUDE ESTIMATION WITH SUPERGAUSSIAN SPEECH MODELING , 2003 .

[19]  Yariv Ephraim.  Gain-adapted hidden Markov models for recognition of clean and noisy speech , 1992, IEEE Trans. Signal Process..

[20]  Ehud Weinstein,et al.  Signal enhancement using beamforming and nonstationarity with applications to speech , 2001, IEEE Trans. Signal Process..

[21]  Li Deng,et al.  Speech Denoising and Dereverberation Using Probabilistic Models , 2000, NIPS.

[22]  R. Balan,et al.  Independent component analysis based single channel speech enhancement , 2003, Proceedings of the 3rd IEEE International Symposium on Signal Processing and Information Technology (IEEE Cat. No.03EX795).

[23]  Sharon Gannot,et al.  Speech enhancement using a mixture-maximum model , 2002, IEEE Trans. Speech Audio Process..

[24]  T. Kristjansson,et al.  High resolution signal reconstruction , 2003, 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721).

[25]  Brendan J. Frey,et al.  Learning Dynamic Noise Models from Noisy Speech for Robust Speech Recognition , 2001 .

[26]  Yariv Ephraim,et al.  Statistical-model-based speech enhancement systems , 1992, Proc. IEEE.

[27]  Hagai Attias,et al.  A Variational Bayesian Framework for Graphical Models , 1999 .

[28]  Li Deng,et al.  A new method for speech denoising and robust speech recognition using probabilistic models for clean speech and for noise , 2001, INTERSPEECH.

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

[30]  Israel Cohen,et al.  Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging , 2003, IEEE Trans. Speech Audio Process..

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

[32]  Jacob Benesty,et al.  Study of the Wiener Filter for Noise Reduction , 2005 .

[33]  Rainer Martin,et al.  Noise power spectral density estimation based on optimal smoothing and minimum statistics , 2001, IEEE Trans. Speech Audio Process..

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

[35]  Peter J. W. Rayner,et al.  Single channel nonstationary stochastic signal separation using linear time-varying filters , 2003, IEEE Trans. Signal Process..

[36]  Yariv Ephraim,et al.  A Bayesian estimation approach for speech enhancement using hidden Markov models , 1992, IEEE Trans. Signal Process..

[37]  A. Czyzewski,et al.  Noise reduction in audio signals based on the perceptual coding approach , 1999, Proceedings of the 1999 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics. WASPAA'99 (Cat. No.99TH8452).