dc.contributor.author | Wester, Mirjam | |
dc.contributor.author | Kessens, Judith M | |
dc.contributor.author | Strik, Helmer | |
dc.coverage.spatial | 4 | en |
dc.date.accessioned | 2006-05-11T16:53:26Z | |
dc.date.available | 2006-05-11T16:53:26Z | |
dc.date.issued | 1998-12 | |
dc.identifier.citation | In ICSLP-1998, paper 0371. | en |
dc.identifier.uri | http://www.isca-speech.org/archive/icslp_1998/index.html | |
dc.identifier.uri | http://hdl.handle.net/1842/1017 | |
dc.description.abstract | This paper describes how the performance of a continuous speech recognizer for Dutch has been improved by modeling pronunciation variation. We used three methods to model pronunciation variation. First, within-word variation was dealt with. Phonological rules were applied to the words in the lexicon, thus automatically generating pronunciation variants. Secondly, cross-word pronunciation variation was modeled using two different approaches. The first approach was to model cross-word processes by adding the variants as separate words to the lexicon and in the second approach this was done by using multi-words. For each of the methods, recognition experiments were carried out. A significant improvement was found for modeling within-word variation. Furthermore, modeling cross-word processes using multi-words leads to significantly better results than modeling them using separate words in the lexicon. | en |
dc.format.extent | 119403 bytes | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | |
dc.publisher | International Speech Communication Association | en |
dc.title | Modeling Pronunciation Variation for a Dutch CSR: Testing Three Methods | en |
dc.type | Conference Paper | en |