5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Fully Automatic Prosody Generator For Text-to-Speech

Fabrice Malfrère (1), Thierry Dutoit (1), Piet Mertens (2)

(1) Faculte Polytechnique de Mons, Belgium
(2) K.U. Leuven - Departement de Linguistique, Belgium

Text-to-Prosody systems based on the use of prosodic databases extracted from natural speech will be a key point for further development of new Text-to-Speech systems. This paper describes a system using such speech databases to generate the rhythm and the intonation of a French written text. The system is based on a very crude chinks 'n chunks prosodic phrasing algorithm and on a prosodic analysis of a natural speech database. The rhythm of the synthetic speech is generated with a CART tree trained on a large mono-speaker speech corpus. The acoustic aspect of the intonation is derived from a set of prosodic patterns automatically derived from the same speech corpus. The system has been tested on single sentences and news paragraphs. Informal listening tests have shown that the resulting prosody is convincing most of the time.

Full Paper
Sound Example
- Synthesized French sentence: 'Le petit canard apprend à nager' (The little duck learns to swim).

Bibliographic reference.  Malfrère, Fabrice / Dutoit, Thierry / Mertens, Piet (1998): "Fully automatic prosody generator for text-to-speech", In ICSLP-1998, paper 0355.