We present here a trainable generative model of French prosody. We focus on the sentence level and design SNNs able to generate both rhythmic and intonation contours for diverse attitudes. First results of a perceptual test show that listeners are able to retrieve the right definition of attitudes by listening to synthetic PSOLA stimuli.

Full Paper

Bibliographic reference.  Morlec, Yann / Bailly, Gérard / Auberge, Véronique (1997): "Synthesising attitudes with global rhythmic and intonation contours", In EUROSPEECH-1997, 219-222.