Show simple item record

dc.contributor.authorCalhoun, Sasha
dc.date.accessioned2007-09-19T12:43:16Z
dc.date.available2007-09-19T12:43:16Z
dc.date.issued2007
dc.identifier.citationSasha Calhoun. Predicting focus through prominence structure. In Proceedings of Interspeech, Antwerp, Belgium, 2007.en
dc.identifier.urihttp://hdl.handle.net/1842/2009
dc.description.abstractFocus is central to our control of information flow in dialogue. Spoken language understanding systems therefore need to be able to detect focus automatically. It is well known that prominence is a key marker of focus in English, however, the relationship is not straight-forward. We present focus prediction models built using the NXT Switchboard corpus. We claim that a focus is more likely if a word is more prominent than expected given its syntactic, semantic and discourse properties. Crucially, the perception of prominence arises not only from acoustic cues, but also the position in prosodic structure. Our focus prediction results, along with a study showing the acoustic properties of focal accents vary by structural position, support our claims. As a largely novel task, these results are an important first step in detecting focus for spoken language applications.en
dc.format.extent346145 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.subjectspeech technologyen
dc.titlePredicting focus through prominence structureen
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record