Keronen, S., Kallasjoki, H., Palomaki, K.J. et al. (2 more authors) (2015) Feature enhancement of reverberant speech by distribution matching and non-negative matrix factorization. EURASIP Journal on Advances in Signal Processing, 76. ISSN 1687-6172
Abstract
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.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2015 Keronen et al. Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License(http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. |
Keywords: | Speech dereverberation; Feature enhancement; Non-negative matrix factorization; Distribution matching |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 29 Oct 2015 14:59 |
Last Modified: | 29 Oct 2015 14:59 |
Published Version: | https://doi.org/10.1186/s13634-015-0259-1 |
Status: | Published |
Publisher: | SpringerOpen |
Refereed: | Yes |
Identification Number: | 10.1186/s13634-015-0259-1 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:90472 |