Enhancement of noisy reverberant speech using polynomial matrix eigenvalue decomposition
Enhancement of noisy reverberant speech using polynomial matrix eigenvalue decomposition
Speech enhancement is important for applications such as telecommunications, hearing aids, automatic speech recognition and voice-controlled systems. Enhancement algorithms aim to reduce interfering noise and reverberation while minimizing any speech distortion. In this work for speech enhancement, we propose to use polynomial matrices to model the spatial, spectral and temporal correlations between the speech signals received by a microphone array and polynomial matrix eigenvalue decomposition (PEVD) to decorrelate in space, time and frequency simultaneously. We then propose a blind and unsupervised PEVD-based speech enhancement algorithm. Simulations and informal listening examples involving diverse reverberant and noisy environments have shown that our method can jointly suppress noise and reverberation, thereby achieving speech enhancement without introducing processing artefacts into the enhanced signal.
Broadband multi-channel signal processing, Correlation, Covariance matrices, Matrix decomposition, Microphones, Noise reduction, Reverberation, Speech enhancement, noise reduction, polynomial matrix eigenvalue decomposition, speech dereverberation, speech enhancement
3255 - 3266
Neo, Vincent W.
7ec5cc5f-8248-40ec-8864-b31335d4ddf2
Evers, Christine
93090c84-e984-4cc3-9363-fbf3f3639c4b
Naylor, Patrick
8c20a1a0-4507-4a0f-8324-f3075354dc52
15 October 2021
Neo, Vincent W.
7ec5cc5f-8248-40ec-8864-b31335d4ddf2
Evers, Christine
93090c84-e984-4cc3-9363-fbf3f3639c4b
Naylor, Patrick
8c20a1a0-4507-4a0f-8324-f3075354dc52
Neo, Vincent W., Evers, Christine and Naylor, Patrick
(2021)
Enhancement of noisy reverberant speech using polynomial matrix eigenvalue decomposition.
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, .
(doi:10.1109/TASLP.2021.3120630).
Abstract
Speech enhancement is important for applications such as telecommunications, hearing aids, automatic speech recognition and voice-controlled systems. Enhancement algorithms aim to reduce interfering noise and reverberation while minimizing any speech distortion. In this work for speech enhancement, we propose to use polynomial matrices to model the spatial, spectral and temporal correlations between the speech signals received by a microphone array and polynomial matrix eigenvalue decomposition (PEVD) to decorrelate in space, time and frequency simultaneously. We then propose a blind and unsupervised PEVD-based speech enhancement algorithm. Simulations and informal listening examples involving diverse reverberant and noisy environments have shown that our method can jointly suppress noise and reverberation, thereby achieving speech enhancement without introducing processing artefacts into the enhanced signal.
Text
Enhancement_of_noisy_reverberant_speech_using_PEVD_r2
- Accepted Manuscript
Restricted to Repository staff only
Request a copy
More information
Accepted/In Press date: 7 October 2021
Published date: 15 October 2021
Additional Information:
Funding Information:
This work was supported in part by Engineering and Physical Sciences Research Council (EPSRC) under Grant EP/S035842/1 and in part by the EPSRC Fellowship underGrant EP/P001017/1.
Publisher Copyright:
© 2014 IEEE.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
Keywords:
Broadband multi-channel signal processing, Correlation, Covariance matrices, Matrix decomposition, Microphones, Noise reduction, Reverberation, Speech enhancement, noise reduction, polynomial matrix eigenvalue decomposition, speech dereverberation, speech enhancement
Identifiers
Local EPrints ID: 453438
URI: http://eprints.soton.ac.uk/id/eprint/453438
ISSN: 2329-9304
PURE UUID: 7d88c443-4d5d-4793-ac0c-57a3302c07a2
Catalogue record
Date deposited: 17 Jan 2022 17:33
Last modified: 17 Mar 2024 04:01
Export record
Altmetrics
Contributors
Author:
Vincent W. Neo
Author:
Christine Evers
Author:
Patrick Naylor
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics