Show simple item record

dc.contributor.convenorF. Castanieen_AU
dc.contributor.authorSo, Stephenen_US
dc.contributor.authorPaliwal, Kuldipen_US
dc.contributor.editorF. Castanieen_US
dc.date.accessioned2017-05-03T13:01:24Z
dc.date.available2017-05-03T13:01:24Z
dc.date.issued2006en_US
dc.date.modified2009-09-21T05:50:08Z
dc.identifier.refurihttp://www.icassp2006.orgen_AU
dc.identifier.doi10.1109/ICASSP.2006.1659989en_AU
dc.identifier.urihttp://hdl.handle.net/10072/12322
dc.description.abstractIn this paper, we report on the recognition accuracy of the multiframe GMM-based block quantiser for the coding of MFCC features in a distributed speech recognition framework under varying noise conditions. All experiments were performed using the ETSI Aurora-2 connected-digits recognition task. For comparison, we have also investigated other quantisation schemes such as the memoryless GMM-based block quantiser, the unconstrained vector quantiser, and non-uniform scalar quantisers. The results show that the rate-distortion efficiency of the quantiser is a factor in determining the level of recognition accuracy at low to medium levels of additive noise. For high levels of additive noise, the influence of rate-distortion efficiency diminishes and the recognition accuracy becomes dependent on the recognition features.en_US
dc.description.peerreviewedYesen_US
dc.description.publicationstatusYesen_AU
dc.format.extent106488 bytes
dc.format.extent44 bytes
dc.format.mimetypeapplication/pdf
dc.format.mimetypetext/plain
dc.languageEnglishen_US
dc.language.isoen_AU
dc.publisherIEEE Signal Processing Societyen_US
dc.publisher.placeNew Jersey, USAen_US
dc.publisher.urihttp://ieeexplore.ieee.org/servlet/opac?punumber=11024en_AU
dc.relation.ispartofstudentpublicationNen_AU
dc.relation.ispartofconferencenameIEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2006en_US
dc.relation.ispartofconferencetitleProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processingen_US
dc.relation.ispartofdatefrom2006-05-14en_US
dc.relation.ispartofdateto2006-05-19en_US
dc.relation.ispartoflocationToulouse, Franceen_US
dc.rights.retentionYen_AU
dc.subject.fieldofresearchcode280206en_US
dc.subject.fieldofresearchcode280204en_US
dc.titleMulti-frame GMM-based block quantisation for distributed speech recognition under noisy conditionsen_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 2006 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en_AU
gro.date.issued2006
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