Multilingual Text Analysis for Text-to-Speech Synthesis
cmp-lg
2008-02-03 v1 计算与语言
摘要
We 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.
引用
@article{arxiv.cmp-lg/9608012,
title = {Multilingual Text Analysis for Text-to-Speech Synthesis},
author = {Richard Sproat},
journal= {arXiv preprint arXiv:cmp-lg/9608012},
year = {2008}
}