Fourth ISCA ITRW on Speech Synthesis
August 29 - September 1, 2001
The model of prosody used for French TTS in the Aculab TTS system is unusual in several respects. Firstly, it is based firmly un current metrical theories of French prosody. Secondly, it is entirely knowledge-based: there are no stochastic components in the model, Thirdly, it makes use of a pseudo-random element to avoid the predictability of synthetic prosody. Fourthly, it is designed to facilitate adaptation to other languages, particularly languages with similar prosody such as Spanish and Italian. The design and implementation of this model are presented here, as well as our plans for its extension to other languages.
Bibliographic reference. Monaghan, Alex / Sannier, Fred (2001): "A metrical model of prosody for French TTS", In SSW4-2001, paper 105.