8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003


Towards the Automatic Extraction of Fujisaki Model Parameters for Mandarin

Hansjorg Mixdorff (1), Hiroya Fujisaki (2), Gao Peng Chen (3), Yu Hu (3)

(1) Berlin University of Applied Sciences, Germany
(2) University of Tokyo, Japan
(3) University of Science and Technology of China, China

The generation of naturally-sounding F0 contours in TTS enhances the intelligibility and perceived naturalness of synthetic speech. In earlier works the first author developed a linguistically motivated model of German intonation based on the quantitative Fujisaki model of the production process of F0, and an automatic procedure for extracting the parameters from the F0 contour which, however, was specific to German. As has been shown by Fujisaki and his co-workers, parametrization of F0 contours of Mandarin requires negative tone commands, as well as a more precise control of F0 associated with the syllabic tones. This paper presents an approach to the automatic parameter estimation for Mandarin, as well as first results concerning the accuracy of estimation. The paper also introduces a recently developed tool for editing Fujisaki parameters featuring resynthesis which will soon be publicly available.

Full Paper

Bibliographic reference.  Mixdorff, Hansjorg / Fujisaki, Hiroya / Chen, Gao Peng / Hu, Yu (2003): "Towards the automatic extraction of fujisaki model parameters for Mandarin", In EUROSPEECH-2003, 873-876.