Show simple item record

dc.contributor.authorWester, Mirjam
dc.contributor.authorFosler-Lussier, Eric
dc.coverage.spatial4en
dc.date.accessioned2006-05-11T13:10:32Z
dc.date.available2006-05-11T13:10:32Z
dc.date.issued2000-10
dc.identifier.citationIn ICSLP-2000, vol.1, 270-273.en
dc.identifier.urihttp://www.isca-speech.org/archive/icslp_2000
dc.identifier.urihttp://hdl.handle.net/1842/987
dc.description.abstractThis paper focuses on modeling pronunciation variation in two different ways: data-derived and knowledge-based. The knowledge-based approach consists of using phonological rules to generate variants. The data-derived approach consists of performing phone recognition, followed by various pruning and smoothing methods to alleviate some of the errors in the phone recognition. Using phonological rules led to a small improvement in WER; whereas, using a data-derived approach in which the phone recognition was smoothed using simple decision trees (d-trees) prior to lexicon generation led to a significant improvement compared to the baseline. Furthermore, we found that 10% of variants generated by the phonological rules were also found using phone recognition, and this increased to 23% when the phone recognition output was smoothed by using d-trees. In addition, we propose a metric to measure confusability in the lexicon and we found that employing this confusion metric to prune variants results in roughly the same improvement as using the d-tree method.en
dc.format.extent56770 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherInternational Speech Communication Associationen
dc.titleA Comparison of Data-Derived and Knowledge-Based Modeling of Pronunciation Variationen
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record