Show simple item record

dc.contributor.authorKoumpis, Konstantinos
dc.contributor.authorRenals, Steve
dc.contributor.authorNiranjan, Mahesan
dc.date.accessioned2006-05-19T15:46:28Z
dc.date.available2006-05-19T15:46:28Z
dc.date.issued2001
dc.identifier.citationKoumpis, Konstantinos / Renals, Steve / Niranjan, Mahesan (2001): "Extractive summarization of voicemail using lexical and prosodic feature subset selection", In EUROSPEECH-2001, 2377-2380.en
dc.identifier.urihttp://www.isca-speech.org/archive/eurospeech_2001/index.html
dc.identifier.urihttp://hdl.handle.net/1842/1145
dc.description.abstractThis paper presents a novel data-driven approach to summarizing spoken audio transcripts utilizing lexical and prosodic features. The former are obtained from a speech recognizer and the latter are extracted automatically from speech waveforms. We employ a feature subset selection algorithm, based on ROC curves, which examines different combinations of features at different target operating conditions. The approach is evaluated on the IBM Voicemail corpus, demonstrating that it is possible and desirable to avoid complete commitment to a single best classifier or feature set.en
dc.format.extent62417 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherInternational Speech Communication Associationen
dc.titleExtractive Summarization of Voicemail using Lexical and Prosodic Feature Subset Selectionen
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record