Show simple item record

dc.contributor.authorBlack, Alan W
dc.contributor.authorLenzo, Kevin
dc.contributor.authorPagel, Vincent
dc.coverage.spatial4en
dc.date.accessioned2006-05-12T13:12:46Z
dc.date.available2006-05-12T13:12:46Z
dc.date.issued1998-11
dc.identifier.citationThird ESCA/COCOSDA Workshop on Speech Synthesis, Jenolan Caves House, Blue Mountains, Australia, November 26-29, 1998. pp.77-80.en
dc.identifier.urihttp://www.isca_speech.org/archive/ssw3
dc.identifier.urihttp://hdl.handle.net/1842/1046
dc.description.abstractIn general text-to-speech systems, it is not possible to guarantee that a lexicon will contain all words found in a text, therefore some system for predicting pronunciation from the word itself is necessary. Here we present a general framework for building letter to sound (LTS) rules from a word list in a language. The technique can be fully automatic, though a small amount of hand seeding can give better results. We have applied this technique to English (UK and US), French and German. The generated models achieve, 75%, 58%, 93% and 89%, respectively, words correct for held out data from the word lists. To test our models on more typical data we also analyzed general text, to find which words do not appear in our lexicon. These unknown words were used as a more realistic test corpus for our models. We also discuss the distribution and type of such unknown words.en
dc.format.extent44358 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherInternational Speech Communication Associationen
dc.titleIssues in Building General Letter to Sound Rulesen
dc.typeConference Paperen


Files in this item

This item appears in the following Collection(s)

Show simple item record