A data-driven method based on a new paradigm is introduced in this paper. We assume that cognitive representations of the discourse are prosodically encoded by means of global multiparametric prototypes. The generation of adequate prosodic contours is then obtained by retrieving and combining these elementary prototypic contours accessed by linguistic or paralinguistic keys. We examine here F0 generation. Two procedures have been applied: the first consists of a superposition model via a structured lexicon, the second uses a recurrent neural network. Preliminary experiments shows that both methods can lead to good quality F0 contours.
Bibliographic reference. Morlec, Yann / Bailly, Gérard / Aubergé, Véronique (1995): "Synthesis and evaluation of intonation with a superposition model", In EUROSPEECH-1995, 2043-2046.