Show simple item record

dc.contributor.authorSo, S
dc.contributor.authorPaliwal, KK
dc.contributor.editorLuís Oliveira
dc.date.accessioned2017-05-03T13:01:32Z
dc.date.available2017-05-03T13:01:32Z
dc.date.issued2005
dc.date.modified2007-03-21T21:26:49Z
dc.identifier.refurihttp://www.interspeech2005.org/
dc.identifier.urihttp://hdl.handle.net/10072/2673
dc.description.abstractIn this paper, we examine a coding scheme for quantising feature vectors in a distributed speech recognition environment that is more robust to noise. It consists of a vector quantiser that operates on the logarithmic filterbank energies (LFBEs). Through the use of a perceptually-weighted Euclidean distance measure, which emphasises the LFBEs that represent the spectral peaks, the vector quantiser codebook provides /emph{a priori} knowledge of the spectral characteristics of clean speech and is used to quantise features from noise-corrupted speech. Our comparative results from the ETSI Aurora-2 recognition task show that the perceptually-weighted vector quantisation of LFBEs achieves higher recognition accuracies for noisy speech than the unweighted vector quantisation, memoryless and multi-frame GMM-based block quantisation and scalar quantisation of Mel frequency-warped cepstral coefficients.
dc.description.peerreviewedYes
dc.description.publicationstatusYes
dc.languageEnglish
dc.language.isoeng
dc.publisherInternational Speech Communication Association (ISCA)
dc.publisher.placeLisbon, Portugal
dc.relation.ispartofstudentpublicationN
dc.relation.ispartofconferencename9th European Conference on Speech Communication and Technology
dc.relation.ispartofconferencetitle9th European Conference on Speech Communication and Technology
dc.relation.ispartofdatefrom2005-09-04
dc.relation.ispartofdateto2005-09-08
dc.relation.ispartoflocationLisbon, Portugal
dc.relation.ispartofpagefrom941
dc.relation.ispartofpageto944
dc.rights.retentionY
dc.subject.fieldofresearchcode280204
dc.subject.fieldofresearchcode280206
dc.titleImproved noise-robustness in distributed speech recognition via perceptually-weighted vector quantisation of filterbank energies
dc.typeConference output
dc.type.descriptionE1 - Conferences
dc.type.codeE - Conference Publications
gro.facultyGriffith Sciences, Griffith School of Engineering
gro.date.issued2005
gro.hasfulltextNo Full Text
gro.griffith.authorPaliwal, Kuldip K.
gro.griffith.authorSo, Stephen


Files in this item

FilesSizeFormatView

There are no files associated with 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