A Non-stationary Noise Suppression Method Based on Particle Filtering and Polyak Averaging

Masakiyo FUJIMOTO; Satoshi NAKAMURA

doi:10.1093/ietisy/e89-d.3.922

A Non-stationary Noise Suppression Method Based on Particle Filtering and Polyak Averaging

Masakiyo FUJIMOTO, Satoshi NAKAMURA

Full Text Views

0

Cite this

Summary :

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 front-end processing of speech recognition in noise. In the proposed method, a noise sequence is estimated in three stages: a sequential importance sampling step, a residual resampling step, and finally a Markov chain Monte Carlo step with Metropolis-Hastings sampling. The estimated noise sequence is used in the MMSE-based clean speech estimation. We also introduce Polyak averaging and feedback into a state transition process for particle filtering. In the evaluation results, we observed that the proposed method improves speech recognition accuracy in the results of non-stationary noise environments a noise compensation method with stationary noise assumptions.

Publication: IEICE TRANSACTIONS on Information Vol.E89-D No.3 pp.922-930

Publication Date: 2006/03/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e89-d.3.922

Type of Manuscript: Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)

Category: Speech Recognition

Cite this

Copy

Masakiyo FUJIMOTO, Satoshi NAKAMURA, "A Non-stationary Noise Suppression Method Based on Particle Filtering and Polyak Averaging" in IEICE TRANSACTIONS on Information, vol. E89-D, no. 3, pp. 922-930, March 2006, doi: 10.1093/ietisy/e89-d.3.922.
Abstract: 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 front-end processing of speech recognition in noise. In the proposed method, a noise sequence is estimated in three stages: a sequential importance sampling step, a residual resampling step, and finally a Markov chain Monte Carlo step with Metropolis-Hastings sampling. The estimated noise sequence is used in the MMSE-based clean speech estimation. We also introduce Polyak averaging and feedback into a state transition process for particle filtering. In the evaluation results, we observed that the proposed method improves speech recognition accuracy in the results of non-stationary noise environments a noise compensation method with stationary noise assumptions.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.3.922/_p

Copy

@ARTICLE{e89-d_3_922,
author={Masakiyo FUJIMOTO, Satoshi NAKAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={A Non-stationary Noise Suppression Method Based on Particle Filtering and Polyak Averaging},
year={2006},
volume={E89-D},
number={3},
pages={922-930},
abstract={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 front-end processing of speech recognition in noise. In the proposed method, a noise sequence is estimated in three stages: a sequential importance sampling step, a residual resampling step, and finally a Markov chain Monte Carlo step with Metropolis-Hastings sampling. The estimated noise sequence is used in the MMSE-based clean speech estimation. We also introduce Polyak averaging and feedback into a state transition process for particle filtering. In the evaluation results, we observed that the proposed method improves speech recognition accuracy in the results of non-stationary noise environments a noise compensation method with stationary noise assumptions.},
keywords={},
doi={10.1093/ietisy/e89-d.3.922},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - A Non-stationary Noise Suppression Method Based on Particle Filtering and Polyak Averaging
T2 - IEICE TRANSACTIONS on Information
SP - 922
EP - 930
AU - Masakiyo FUJIMOTO
AU - Satoshi NAKAMURA
PY - 2006
DO - 10.1093/ietisy/e89-d.3.922
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2006
AB - 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 front-end processing of speech recognition in noise. In the proposed method, a noise sequence is estimated in three stages: a sequential importance sampling step, a residual resampling step, and finally a Markov chain Monte Carlo step with Metropolis-Hastings sampling. The estimated noise sequence is used in the MMSE-based clean speech estimation. We also introduce Polyak averaging and feedback into a state transition process for particle filtering. In the evaluation results, we observed that the proposed method improves speech recognition accuracy in the results of non-stationary noise environments a noise compensation method with stationary noise assumptions.
ER -