Show simple item record

dc.contributor.authorClark, Robert A J
dc.contributor.authorRichmond, Korin
dc.contributor.authorKing, Simon
dc.date.accessioned2006-05-08T16:33:48Z
dc.date.available2006-05-08T16:33:48Z
dc.date.issued2005
dc.identifier.citationIn Proc. Interspeech 2005, September 2005en
dc.identifier.urihttp://hdl.handle.net/1842/919
dc.description.abstractThis paper describes the process of building unit selection voices for the Festival Multisyn engine using four ARCTIC datasets, as part of the Blizzard evaluation challenge. The build process is almost entirely automatic, with very little need for human intervention. We discuss the difference in the evaluation results for each voice and evaluate the suitability of the ARCTIC datasets for building this type of voice.en
dc.format.extent298291 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherInternational Speech Communication Associationen
dc.subjectspeech synthesisen
dc.subjectfestivalen
dc.subjectARCTIC datasetsen
dc.subjectMultisynen
dc.titleMultisyn voices from ARCTIC data for the Blizzard challenge.en
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record