Show simple item record

dc.contributor.authorGibson, Matthew
dc.contributor.authorHirsimaki, T
dc.contributor.authorKarhila, R
dc.contributor.authorKurimo, M
dc.contributor.authorByrne, William
dc.date.accessioned2010-08-25T16:14:50Z
dc.date.available2010-08-25T16:14:50Z
dc.date.issued2010
dc.identifier.isbn9781424442959
dc.identifier.urihttp://www.dspace.cam.ac.uk/handle/1810/226329
dc.description.abstractThis paper demonstrates how unsupervised cross-lingual adaptation of HMM-based speech synthesis models may be performed without explicit knowledge of the adaptation data language. A two-pass decision tree construction technique is deployed for this purpose. Using parallel translated datasets, cross-lingual and intralingual adaptation are compared in a controlled manner. Listener evaluations reveal that the proposed method delivers performance approaching that of unsupervised intralingual adaptation.
dc.format.mediumpaper
dc.publisherIEEE
dc.titleUnsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction
dc.typeConference Object
prism.endingPage4645
prism.publicationDate2010
prism.publicationNameProceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
prism.startingPage4642
rioxxterms.versionofrecord10.1109/ICASSP.2010.5495196
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2010
dc.publisher.urlhttp://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=5487364
rioxxterms.typeConference Paper/Proceeding/Abstract
pubs.funder-project-idEuropean Commission (213845)
dc.identifier.urlhttp://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=5487364
pubs.conference-nameIEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP' 10
pubs.conference-start-date2010-03-14
pubs.conference-finish-date2010-03-19


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record