Sequential Non-Stationary Noise Tracking Using Particle Filtering with Switching Dynamical System

This paper addresses a speech recognition problem in non-stationary noise environments: the estimation of noise sequences. To solve this problem, we present a particle filter-based sequential noise estimation method for the front-end processing of speech recognition. In the proposed method, the particle filter is defined by a dynamical system based on Polyak averaging and feedback. We also introduce a switching dynamical system into the particle filter to cope with the state transition characteristics of non-stationary noise. In the evaluation results, we observed that the proposed method improves speech recognition accuracy in the results of non-stationary noise environments by a noise compensation method with stationary noise assumptions

[1]  Olivier Siohan,et al.  Sequential estimation with optimal forgetting for robust speech recognition , 2004, IEEE Transactions on Speech and Audio Processing.

[2]  H. Kushner,et al.  Stochastic approximation with averaging and feedback: rapidly convergent "on-line" algorithms , 1995, IEEE Trans. Autom. Control..

[3]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[4]  Satoshi Nakamura,et al.  Noise adaptive speech recognition based on sequential noise parameter estimation , 2004, Speech Commun..

[5]  Satoshi Nakamura,et al.  Online cepstral filtering using a sequential EM approach with Polyak averaging and feedback [speech recognition applications] , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[6]  W. K. Hastings,et al.  Monte Carlo Sampling Methods Using Markov Chains and Their Applications , 1970 .

[7]  S. Nakamura,et al.  Sequential Noise Compensation by Sequential Monte Carlo Method , 2001, NIPS.

[8]  Antonio M. Peinado,et al.  Model-based compensation of the additive noise for continuous speech recognition. experiments using the Aurora II database and tasks , 2001, INTERSPEECH.

[9]  Kristine L. Bell,et al.  A Tutorial on Particle Filters for Online Nonlinear/NonGaussian Bayesian Tracking , 2007 .

[10]  Satoshi Nakamura,et al.  AURORA-2J: An Evaluation Framework for Japanese Noisy Speech Recognition , 2005, IEICE Trans. Inf. Syst..

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

[12]  Olivier Siohan,et al.  Sequential noise estimation with optimal forgetting for robust speech recognition , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[13]  Alex Acero,et al.  Noise robust speech recognition with a switching linear dynamic model , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[14]  S. Nakamura,et al.  Particle filtering and Polyak averaging-based non-stationary noise tracking for ASR in noise , 2005, IEEE Workshop on Automatic Speech Recognition and Understanding, 2005..