Integrating prosodic and lexical cues for automatic topic segmentation

dc.citation.epage57en_US
dc.citation.issueNumber1en_US
dc.citation.spage31en_US
dc.citation.volumeNumber27en_US
dc.contributor.authorTür G.en_US
dc.contributor.authorStolcke, A.en_US
dc.contributor.authorHakkani-Tür, D.en_US
dc.contributor.authorShriberg, E.en_US
dc.date.accessioned2016-02-08T10:35:43Z
dc.date.available2016-02-08T10:35:43Z
dc.date.issued2001en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractWe present a probabilistic model that uses both prosodic and lexical cues for the automatic segmentation of speech into topically coherent units. We propose two methods for combining lexical and prosodic information using hidden Markov models and decision trees. Lexical information is obtained from a speech recognizer, and prosodic features are extracted automatically from speech waveforms. We evaluate our approach on the Broadcast News corpus, using the DARPA-TDT evaluation metrics. Results show that the prosodic model alone is competitive with word-based segmentation methods. Furthermore, we achieve a significant reduction in error by combining the prosodic and word-based knowledge sources.en_US
dc.identifier.doi10.1162/089120101300346796en_US
dc.identifier.issn0891-2017en_US
dc.identifier.urihttp://hdl.handle.net/11693/24885en_US
dc.language.isoEnglishen_US
dc.relation.isversionofhttp://dx.doi.org/10.1162/089120101300346796en_US
dc.source.titleComputational Linguisticsen_US
dc.titleIntegrating prosodic and lexical cues for automatic topic segmentationen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Integrating prosodic and lexical cues for automatic topic segmentation.pdf
Size:
272.08 KB
Format:
Adobe Portable Document Format
Description:
Full printable version