Incorporating multi-channel Wiener Filter with single-channel speech enhancement algorithm 2013

The real-time implementation of the existing multi-channel Wiener filter (MWF) algorithms suffer from performance degradation due to the lack of robustness against estimation errors of the second-order statistics. The reasons are twofold: one, the estimation of the statistics relies on real voice ac...

Full description

Bibliographic Details
Main Authors: Yong, Pei Chee, Nordholm, Sven, Dam, Hai Huyen, Leung, Yee-Hong, Lai, Chiong Ching
Other Authors: Not known
Format: Conference Paper
Published: The Institute of Electrical and Electronic Engineers 2013
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/45997
_version_ 1848757438960893952
author Yong, Pei Chee
Nordholm, Sven
Dam, Hai Huyen
Leung, Yee-Hong
Lai, Chiong Ching
author2 Not known
author_facet Not known
Yong, Pei Chee
Nordholm, Sven
Dam, Hai Huyen
Leung, Yee-Hong
Lai, Chiong Ching
author_sort Yong, Pei Chee
building Curtin Institutional Repository
collection Online Access
description The real-time implementation of the existing multi-channel Wiener filter (MWF) algorithms suffer from performance degradation due to the lack of robustness against estimation errors of the second-order statistics. The reasons are twofold: one, the estimation of the statistics relies on real voice activity detector (VAD), which often fails in adverse environments. Second, the MWF solutions involve estimation of the second order clean speech statistics, which also exaggerates the errors. This paper presents an MWF algorithm that requires neither VAD nor clean speech statistics. Performance evaluation under real scenarios shows that the proposed method outperforms the conventional MWF solution in terms of the trade-off between noise reduction and speech distortion.
first_indexed 2025-11-14T09:28:06Z
format Conference Paper
id curtin-20.500.11937-45997
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:28:06Z
publishDate 2013
publisher The Institute of Electrical and Electronic Engineers
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-459972017-09-13T14:30:05Z Incorporating multi-channel Wiener Filter with single-channel speech enhancement algorithm 2013 Yong, Pei Chee Nordholm, Sven Dam, Hai Huyen Leung, Yee-Hong Lai, Chiong Ching Not known Multi-channel Wiener filter speech enhancement single-channel noise reduction The real-time implementation of the existing multi-channel Wiener filter (MWF) algorithms suffer from performance degradation due to the lack of robustness against estimation errors of the second-order statistics. The reasons are twofold: one, the estimation of the statistics relies on real voice activity detector (VAD), which often fails in adverse environments. Second, the MWF solutions involve estimation of the second order clean speech statistics, which also exaggerates the errors. This paper presents an MWF algorithm that requires neither VAD nor clean speech statistics. Performance evaluation under real scenarios shows that the proposed method outperforms the conventional MWF solution in terms of the trade-off between noise reduction and speech distortion. 2013 Conference Paper http://hdl.handle.net/20.500.11937/45997 10.1109/ICASSP.2013.6639077 The Institute of Electrical and Electronic Engineers restricted
spellingShingle Multi-channel Wiener filter
speech enhancement
single-channel noise reduction
Yong, Pei Chee
Nordholm, Sven
Dam, Hai Huyen
Leung, Yee-Hong
Lai, Chiong Ching
Incorporating multi-channel Wiener Filter with single-channel speech enhancement algorithm 2013
title Incorporating multi-channel Wiener Filter with single-channel speech enhancement algorithm 2013
title_full Incorporating multi-channel Wiener Filter with single-channel speech enhancement algorithm 2013
title_fullStr Incorporating multi-channel Wiener Filter with single-channel speech enhancement algorithm 2013
title_full_unstemmed Incorporating multi-channel Wiener Filter with single-channel speech enhancement algorithm 2013
title_short Incorporating multi-channel Wiener Filter with single-channel speech enhancement algorithm 2013
title_sort incorporating multi-channel wiener filter with single-channel speech enhancement algorithm 2013
topic Multi-channel Wiener filter
speech enhancement
single-channel noise reduction
url http://hdl.handle.net/20.500.11937/45997