Show simple item record

dc.contributor.authorYong, Pei Chee
dc.contributor.authorNordholm, Sven
dc.contributor.authorDam, Hai Huyen
dc.contributor.authorLeung, Yee-Hong
dc.contributor.authorLai, Chiong Ching
dc.contributor.editorNot known
dc.date.accessioned2017-01-30T15:24:36Z
dc.date.available2017-01-30T15:24:36Z
dc.date.created2014-02-17T20:00:53Z
dc.date.issued2013
dc.identifier.citationYong, Pei Chee and Nordholm, Sven and Dam, Hai Huyen and Leung, Yee Hong and Lai, Chiong Ching. 2013. Incorporating multi-channel Wiener Filter with single-channel speech enhancement algorithm 2013, in International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 26-31 2013, pp. 7284-7288. Vancouver, Canada: The Institute of Electrical and Electronic Engineers.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/45997
dc.identifier.doi10.1109/ICASSP.2013.6639077
dc.description.abstract

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.

dc.publisherThe Institute of Electrical and Electronic Engineers
dc.subjectMulti-channel Wiener filter
dc.subjectspeech enhancement
dc.subjectsingle-channel noise reduction
dc.titleIncorporating multi-channel Wiener Filter with single-channel speech enhancement algorithm 2013
dc.typeConference Paper
dcterms.source.startPage7284
dcterms.source.endPage7288
dcterms.source.titleProceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
dcterms.source.seriesProceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
dcterms.source.isbn9781479903566
dcterms.source.conferenceIEEE International Conference on Acoustics, Speech and Signal Processing
dcterms.source.conference-start-dateMay 26 2013
dcterms.source.conferencelocationVancouver, Canada
dcterms.source.placeVancouver, Canada
curtin.department
curtin.accessStatusFulltext not available


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record