Show simple item record

In Proc. Interspeech 2009, Brighton, U.K., September 2009

dc.contributor.authorBadino, Leonardo
dc.contributor.authorAndersson, J. Sebastian
dc.contributor.authorYamagishi, Junichi
dc.contributor.authorClark, Robert A J
dc.date.accessioned2010-10-13T15:00:54Z
dc.date.available2010-10-13T15:00:54Z
dc.date.issued2009en
dc.identifier.urihttp://hdl.handle.net/1842/3963
dc.description.abstractThe work presented in this paper proposes to identify contrast in the form of contrastive word pairs and prosodically signal it with emphatic accents in a Text-to-Speech (TTS) application using a Hidden-Markov-Model (HMM) based speech synthesis system. We first describe a novel method to automatically detect contrastive word pairs using textual features only and report its performance on a corpus of spontaneous conversations in English. Subsequently we describe the set of features selected to train a HMM-based speech synthesis system and attempting to properly control prosodic prominence (including emphasis). Results from a large scale perceptual test show that in the majority of cases listeners judge emphatic contrastive word pairs as acceptable as their non-emphatic counterpart, while emphasis on non-contrastive pairs is almost never acceptable.en
dc.titleIdentification of Contrast and Its Emphatic Realization in HMM-based Speech Synthesisen
dc.typeConference Paperen
rps.titleIn Proc. Interspeech 2009, Brighton, U.K., September 2009en
dc.date.updated2010-10-13T15:00:54Z
dc.date.openingDate2009


Files in this item

This item appears in the following Collection(s)

Show simple item record