Audiovisual text-to-cued speech synthesis

We present here our efforts for characterizing the 3D movements of the right hand and the face of a French female during the production of manual cued speech. We analyzed the 3D trajectories of 50 hand and 63 facial fleshpoints during the production of 238 utterances carefully designed for covering all possible diphones of the French language. Linear and non linear statistical models of the hand and face deformations and postures have been developed using both separate and joint corpora. We implement a concatenative audiovisual text-to-cued speech synthesis system.