Codebook-Based Bayesian Speech Enhancement for Nonstationary Environments

In this paper, we propose a Bayesian minimum mean squared error approach for the joint estimation of the short-term predictor parameters of speech and noise, from the noisy observation. We use trained codebooks of speech and noise linear predictive coefficients to model the a priori information requ...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on audio, speech, and language processing speech, and language processing, 2007-02, Vol.15 (2), p.441-452
Main Authors: Srinivasan, S., Samuelsson, J., Kleijn, W.B.
Format: Article
Language:English
Subjects:
Acoustic noise
Applied sciences
Background noise
Bayesian
Bayesian analysis
Bayesian methods
Codebooks
Coding, codes
Detection, estimation, filtering, equalization, prediction
Errors
Estimates
Exact sciences and technology
Frames
Information technology
Information, signal and communications theory
Informationsteknik
Linear predictive coding
Mathematical models
Mobile communication
Noise
Noise estimation
Signal and communications theory
Signal processing
Signal, noise
Speech
Speech coding
Speech enhancement
Speech processing
State of the art
Statistics
Studies
TECHNOLOGY
TEKNIKVETENSKAP
Telecommunication
Telecommunications and information theory
Telekommunikation
Wiener filter
Wiener filtering
Working environment noise
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a Bayesian minimum mean squared error approach for the joint estimation of the short-term predictor parameters of speech and noise, from the noisy observation. We use trained codebooks of speech and noise linear predictive coefficients to model the a priori information required by the Bayesian scheme. In contrast to current Bayesian estimation approaches that consider the excitation variances as part of the a priori information, in the proposed method they are computed online for each short-time segment, based on the observation at hand. Consequently, the method performs well in nonstationary noise conditions. The resulting estimates of the speech and noise spectra can be used in a Wiener filter or any state-of-the-art speech enhancement system. We develop both memoryless (using information from the current frame alone) and memory-based (using information from the current and previous frames) estimators. Estimation of functions of the short-term predictor parameters is also addressed, in particular one that leads to the minimum mean squared error estimate of the clean speech signal. Experiments indicate that the scheme proposed in this paper performs significantly better than competing methods
ISSN:1558-7916
2329-9290
1063-6676
1558-2353
1558-7924
2329-9304
DOI:10.1109/TASL.2006.881696