DocumentCode
2314416
Title
Multilingual text analysis for text-to-speech synthesis
Author
Sproat, Richard
Author_Institution
Dept. of Speech Synthesis Res., AT&T Bell Labs., Murray Hill, NJ, USA
Volume
3
fYear
1996
fDate
3-6 Oct 1996
Firstpage
1365
Abstract
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
Keywords
finite state machines; linguistics; natural language interfaces; speech synthesis; Bell Labs TTS system; French; German; Italian; Japanese; Mandarin; Romanian; Russian; Spanish; declarative descriptions; lexical toolkit; lexicons; morphological rules; multilingual text analysis; numeral expansion rules; phonological rules; text-to-speech synthesis; weighted finite state transducers; Natural languages; Speech synthesis; Text analysis; Transducers;
fLanguage
English
Publisher
ieee
Conference_Titel
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on
Conference_Location
Philadelphia, PA
Print_ISBN
0-7803-3555-4
Type
conf
DOI
10.1109/ICSLP.1996.607867
Filename
607867
Link To Document