Capturing data and realistic 3D models for cued speech analysis and audiovisual synthesis

Frédéric Elisei (1) , Gérard Bailly (1) , Guillaume Gibert (1) , Rémi Brun (2)

1 ICP - Institut de la communication parlée
2 Attitude Studio

We have implemented a complete text-to-speech synthesis system by concatenation that addresses French Manual Cued Speech (FMCS). It uses two separate dictionaries, one for multimodal diphones with audio and facial articulation, and the other with the gestures between two consecutive FMCS keys (“dikeys”). Dictionaries were built from real data.

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Frédéric Elisei, Gérard Bailly, Guillaume Gibert, Rémi Brun. Capturing data and realistic 3D models for cued speech analysis and audiovisual synthesis. Auditory-Visual Speech Processing Workshop, 2005, Vancouver, Canada. pp.125-130. ⟨hal-00419311⟩