DocumentCode
2862319
Title
The use of a generative model of F0 contours for multilingual speech synthesis
Author
Fujisaki, H. ; Ohno, Siimio
Author_Institution
Dept. of Appl. Electron., Tokyo Sci. Univ., Japan
fYear
1998
fDate
1998
Firstpage
714
Abstract
This paper describes the command-response model for FO contour generation originally developed for common Japanese, and demonstrates its capability of generating FO contours of various other languages with minor language-specific modifications. The model is especially useful in multilingual speech synthesis, since the same mechanism can be driven by language-specific patterns of input commands to produce FO contours of utterances of the respective languages
Keywords
speech synthesis; Japanese; command-response model; contour generation; generative model; input commands; language-specific modifications; multilingual speech synthesis; utterances; Control systems; Electronic mail; Equations; Frequency; Linear systems; Natural languages; Pulse generation; Shape; Speech synthesis; Vibration control;
fLanguage
English
Publisher
ieee
Conference_Titel
Signal Processing Proceedings, 1998. ICSP '98. 1998 Fourth International Conference on
Conference_Location
Beijing
Print_ISBN
0-7803-4325-5
Type
conf
DOI
10.1109/ICOSP.1998.770311
Filename
770311
Link To Document