Single-channel online enhancement of speech corrupted by reverberation and noise

File Description SizeFormat 
07795155.pdfPublished version1.49 MBAdobe PDFView/Open
Title: Single-channel online enhancement of speech corrupted by reverberation and noise
Authors: Doire, CSJ
Brookes, DM
Naylor, PA
Hicks, CM
Betts, D
Dmour, MA
Jensen, SH
Item Type: Journal Article
Abstract: This paper proposes an online single-channel speech enhancement method designed to improve the quality of speech degraded by reverberation and noise. Based on an auto-regressive model for the reverberation power and on a Hidden Markov Model for clean speech production, a Bayesian filtering formulation of the problem is derived and online joint estimation of the acoustic parameters and mean speech, reverberation and noise powers is obtained in Mel-frequency bands. From these estimates, a real-valued spectral gain is derived and spectral enhancement is applied in the STFT domain. The method yields state-of-the-art performance and greatly reduces the effects of reverberation and noise while improving speech quality and preserving speech intelligibility in challenging acoustic environments.
Issue Date: 22-Dec-2016
Date of Acceptance: 15-Dec-2016
URI: http://hdl.handle.net/10044/1/43267
DOI: https://dx.doi.org/10.1109/TASLP.2016.2641904
ISSN: 1558-7924
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Start Page: 572
End Page: 587
Journal / Book Title: IEEE Transactions on Audio Speech and Language Processing
Volume: 25
Issue: 3
Copyright Statement: © 2016 IEEE. This work is licensed under a Creative Commons Attribution 3.0 License. For more information, see http://creativecommons.org/licenses/by/3.0/
Sponsor/Funder: Commission of the European Communities
Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: PITN-GA-2012-316969
ep/m026698/1
Keywords: Science & Technology
Technology
Acoustics
Engineering, Electrical & Electronic
Engineering
Dereverberation
speech
Bayesian
single-channel
MULTICHANNEL LINEAR PREDICTION
HIDDEN MARKOV-MODELS
SPECTRAL SUBTRACTION
DEREVERBERATION
INTELLIGIBILITY
RECOGNITION
SUPPRESSION
ALGORITHM
Speech
Single-channel
Speech-Language Pathology & Audiology
09 Engineering
17 Psychology And Cognitive Sciences
20 Language, Communication And Culture
Publication Status: Published
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx