Article

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

DOI:http://dx.doi.org/10.1093/ietisy/e89-d.3.922
Source: OAI

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.

0 0
 · 
0 Bookmarks
 · 
21 Views
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.

Keywords

estimated noise sequence
 
front-end processing
 
Markov chain Monte Carlo step
 
noise compensation method
 
noise sequence
 
noise sequences
 
non-stationary noise environments
 
particle filter-based sequential noise estimation method
 
Polyak
 
proposed method
 
residual resampling step
 
sequential importance sampling step
 
speech estimation
 
speech recognition
 
speech recognition accuracy
 
speech recognition problem
 
state transition process
 
stationary noise assumptions