Show simple item record

dc.contributor.authorStrom, Volker
dc.coverage.spatial4en
dc.date.accessioned2006-05-10T17:31:43Z
dc.date.available2006-05-10T17:31:43Z
dc.date.issued2002-09
dc.identifier.citationIn Proceedings [ICSLP-2002] 7th International Conference on Spoken Language Processing (ICSLP2002 - INTERSPEECH 2002), Denver, Colorado, USA, September 16-20, 2002en
dc.identifier.urihttp://www.isca-speech.org/archive/icslp02
dc.identifier.urihttp://hdl.handle.net/1842/957
dc.description.abstractA new method for predicting prosodic parameters, i.e. phone durations and F0 targets, from preprocessed text is presented. The prosody model comprises a set of CARTs, which are learned from a large database of labeled speech. This database need not be annotated with Tone and Break Indices (ToBI labels). Instead, a simpler symbolic prosodic description is created by a bootstrapping method. The method had been applied to one Spanish and two German speakers. For the German voices, two listening tests showed a significant preference for the new method over a more traditional approach of prosody prediction, based on hand-crafted rules.en
dc.format.extent42545 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherInternational Speech Communication Associationen
dc.titleFrom text to prosody without ToBIen
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record