Third ESCA/COCOSDA Workshop on Speech Synthesis

November 26-29, 1998
Jenolan Caves House, Blue Mountains, NSW, Australia

A Command-Response Model for F0 Contour Generation in Multilingual Speech Synthesis

Hiroya Fujisaki (1), Sumio Ohno (1), Changfu Wang (2)

(1) Department of Applied Electronics, Science University of Tokyo, Noda, Japan
(2) Department of Electronic Engineering, University of Science and Technology of China Hefei, Anhui, China

This paper describes the command-response model for F0 contour generation originally developed for the common Japanese, and demonstrates its capability of generating F0 contours of various other languages. It is shown that intonations of various languages are produced by language-specific patterns of input commands, while the response mechanisms are essentially identical in speakers of various languages, thus making the model especially useful for multilingual speech synthesis.


Full Paper

Bibliographic reference.  Fujisaki, Hiroya / Ohno, Sumio / Wang, Changfu (1998): "A Command-Response Model for F0 Contour Generation in Multilingual Speech Synthesis", In SSW3-1998, 299-304.