Show simple item record

dc.contributor.authorSo, Stephenen_US
dc.contributor.authorPaliwal, Kuldipen_US
dc.contributor.editorJanet Fletcher, Deborah Loakesen_US
dc.date.accessioned2017-05-03T13:01:26Z
dc.date.available2017-05-03T13:01:26Z
dc.date.issued2008en_US
dc.date.modified2013-05-28T04:39:58Z
dc.identifier.refurihttp://www.interspeech2008.org/en_US
dc.identifier.urihttp://hdl.handle.net/10072/21299
dc.description.abstractIn this paper, we investigate a long state vector Kalman filter for the enhancement of speech that has been corrupted by white and coloured noise. It has been reported in previous studies that a vector Kalman filter achieves better enhancement than the scalar Kalman filter and it is expected that by increasing the state vector length, one may improve the enhancement performance even further. However, any enhancement improvement that may result from an increase in state vector length is constrained by the typical use of short, non-overlapped speech frames, as the autocorrelation coefficient estimates tend to become less reliable at higher lags. We propose to overcome this problem by incorporating an analysis-modification-synthesis framework, where long, overlapped frames are used instead. Our enhancement experiments based on the NOIZEUS corpus show that the proposed long state vector Kalman filter achieves higher mean SNR and PESQ scores than the scalar and short state vector Kalman filter, therefore fulfilling the notion that a longer state vector can lead to better enhancement.en_US
dc.description.peerreviewedYesen_US
dc.description.publicationstatusYesen_US
dc.format.extent656776 bytes
dc.format.mimetypeapplication/pdf
dc.languageEnglishen_US
dc.language.isoen_US
dc.publisherInternational Speech Communication Associationen_US
dc.publisher.placeLisbon, Portugalen_US
dc.publisher.urihttp://www.isca-speech.org/index.phpen_US
dc.publisher.urihttp://www.interspeech2008.org/en_US
dc.relation.ispartofstudentpublicationNen_US
dc.relation.ispartofconferencenameInterspeech 2008 incorporating SST 2008en_US
dc.relation.ispartofconferencetitleProceedings of the 9th Annual Conference of the International Speech Communication Associationen_US
dc.relation.ispartofdatefrom2008-09-22en_US
dc.relation.ispartofdateto2008-09-26en_US
dc.relation.ispartoflocationAustraliaen_US
dc.rights.retentionYen_US
dc.subject.fieldofresearchcode280204en_US
dc.titleA long state vector Kalman filter for speech enhancementen_US
dc.typeConference outputen_US
dc.type.descriptionE1 - Conference Publications (HERDC)en_US
dc.type.codeE - Conference Publicationsen_US
gro.facultyGriffith Sciences, Griffith School of Engineeringen_US
gro.rights.copyrightCopyright 2008 ISCA and the Authors. The attached file is reproduced here in accordance with the copyright policy of the publisher. For information about this conference please refer to the conference’s website or contact the authors.en_US
gro.date.issued2008
gro.hasfulltextFull Text


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record