Show simple item record

dc.contributor.authorNenkova, Ani
dc.contributor.authorBrenier, Jason
dc.contributor.authorKothari, Anubha
dc.contributor.authorCalhoun, Sasha
dc.contributor.authorWhitton, Laura
dc.contributor.authorBeaver, David
dc.contributor.authorJurafsky, Daniel
dc.date.accessioned2007-09-19T12:42:49Z
dc.date.available2007-09-19T12:42:49Z
dc.date.issued2007
dc.identifier.citationAni Nenkova, Jason Brenier, Anubha Kothari, Sasha Calhoun, Laura Whitton, David Beaver, and Dan Jurafsky. To memorize or to predict: Prominence labeling in conversational speech. In NAACL Human Language Technology Conference, Rochester, NY, 2007en
dc.identifier.urihttp://hdl.handle.net/1842/2007
dc.description.abstractThe immense prosodic variation of natural conversational speech makes it challenging to predict which words are prosodically prominent in this genre. In this paper, we examine a new feature, accent ratio, which captures how likely it is that a word will be realized as prominent or not. We compare this feature with traditional accent prediction features (based on part of speech and N-grams) as well as with several linguistically motivated and manually labeled information structure features, such as whether a word is given, new, or contrastive. Our results show that the linguistic features do not lead to significant improvements, while accent ratio alone can yield prediction performance almost as good as the combination of any other subset of features. Moreover, this feature is useful even across genres; an accent-ratio classifier trained only on conversational speech predicts prominence with high accuracy in broadcast news. Our results suggest that carefully chosen lexicalized features can outperform less fine-grained features.en
dc.format.extent87084 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.subjectspeech technologyen
dc.titleTo memorize or to predict: Prominence labeling in conversational speechen
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record