Multilingual Text Analysis for Text-to-Speech Synthesis

Simple item page
dc.creatorSproat, Richard
dc.date1996-08-19
dc.date.accessioned2026-07-07T09:10:36Z
dc.date.available2026-07-07T09:10:36Z
dc.descriptionWe present a model of text analysis for text-to-speech (TTS) synthesis based on (weighted) finite-state transducers, which serves as the text-analysis module of the multilingual Bell Labs TTS system. The transducers are constructed using a lexical toolkit that allows declarative descriptions of lexicons, morphological rules, numeral-expansion rules, and phonological rules, inter alia. To date, the model has been applied to eight languages: Spanish, Italian, Romanian, French, German, Russian, Mandarin and Japanese.
dc.identifierhttps://arxiv.org/abs/cmp-lg/9608012
dc.identifierhttp://arxiv.org/abs/cmp-lg/9608012
dc.identifierECAI Workshop on Extended Finite-State Models of Language
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151396
dc.subjectComputation and Language
dc.titleMultilingual Text Analysis for Text-to-Speech Synthesis
dc.typetext

Files

Collections

arXiv