Show simple item record

dc.contributor.authorGarau, Giulia
dc.contributor.authorRenals, Steve
dc.contributor.authorHain, Thomas
dc.date.accessioned2006-05-08T16:33:38Z
dc.date.available2006-05-08T16:33:38Z
dc.date.issued2005
dc.identifier.citationIn Proceedings, Interspeech'2005 - Eurospeech, 9th European Conference on Speech Communication and Technology, Lisbon, Portugal, September 4-8, 2005en
dc.identifier.urihttp://www.isca-speech.org/archive/interspeech_2005
dc.identifier.urihttp://hdl.handle.net/1842/918
dc.description.abstractVocal Tract Length Normalisation (VTLN) is a commonly used technique to normalise for inter-speaker variability. It is based on the speaker-specific warping of the frequency axis, parameterised by a scalar warp factor. This factor is typically estimated using maximum likelihood. We discuss how VTLN may be applied to multiparty conversations, reporting a substantial decrease in word error rate in experiments using the ICSI meetings corpus. We investigate the behaviour of the VTLN warping factor and show that a stable estimate is not obtained. Instead it appears to be influenced by the context of the meeting, in particular the current conversational partner. These results are consistent with predictions made by the psycholinguistic interactive alignment account of dialogue, when applied at the acoustic and phonological levels.en
dc.format.extent87732 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherInternational Speech Communication Associationen
dc.subjectVocal Tract Length Normalisationen
dc.subjectinter-speaker variabilityen
dc.titleApplying Vocal Tract Length Normalization to Meeting Recordingsen
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record