Show simple item record

dc.contributor.authorKessens, Judith M
dc.contributor.authorWester, Mirjam
dc.contributor.authorStrik, Helmer
dc.date.accessioned2006-05-26T10:46:15Z
dc.date.available2006-05-26T10:46:15Z
dc.date.issued1999
dc.identifier.citationIn Proc. of ICPhS '99, pages 1665-1668, San Francisco, 1999.en
dc.identifier.urihttp://hdl.handle.net/1842/1174
dc.description.abstractThis paper describes how the performance of a continuous speech recognizer for Dutch has been improved by modeling within-word and cross-word pronunciation variation. Within-word variants were automatically generated by applying five phonological rules to the words in the lexicon. For the within-word method, a significant improvement is found compared to the baseline. Cross-word pronunciation variation was modeled using two different methods: 1) adding cross-word variants directly to the lexicon, 2) only adding multi-words and their variants to the lexicon. Overall, cross-word method 2 leads to better results than cross-word method 1. The best results were obtained when cross-word method 2 was combined with the within-word method: a relative improvement of 8.8% WER was found compared to the baseline.en
dc.format.extent50834 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherInternational Congress of Phonetic Sciencesen
dc.titleModeling within-word and cross-word pronunciation variation to improve the performance of a Dutch CSR.en
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record