Feature enhancement of reverberant speech by distribution matching and non-negative matrix factorization

This paper describes a novel two-stage dereverberation feature enhancement method for noise-robust automatic speech recognition. In the first stage, an estimate of the dereverberated speech is generated by matching the distribution of the observed reverberant speech to that of clean speech, in a dec...

Full description

Saved in:
Bibliographic Details
Published in:EURASIP journal on advances in signal processing 2015-08, Vol.2015 (1), p.1-14, Article 76
Main Authors: Keronen, Sami, Kallasjoki, Heikki, Palomäki, Kalle J., Brown, Guy J., Gemmeke, Jort F.
Format: Article
Language:English
Subjects:
Cleaning
Distortion
Engineering
Estimates
Factorization
Matching
Quantum Information Technology
Signal,Image and Speech Processing
Speech
Spintronics
State of the art
Transformations
‘Silencing the Echoes’ – Processing of Reverberant Speech
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper describes a novel two-stage dereverberation feature enhancement method for noise-robust automatic speech recognition. In the first stage, an estimate of the dereverberated speech is generated by matching the distribution of the observed reverberant speech to that of clean speech, in a decorrelated transformation domain that has a long temporal context in order to address the effects of reverberation. The second stage uses this dereverberated signal as an initial estimate within a non-negative matrix factorization framework, which jointly estimates a sparse representation of the clean speech signal and an estimate of the convolutional distortion. The proposed feature enhancement method, when used in conjunction with automatic speech recognizer back-end processing, is shown to improve the recognition performance compared to three other state-of-the-art techniques.
ISSN:1687-6180
1687-6172
1687-6180
DOI:10.1186/s13634-015-0259-1