Characterization of cued speech vowels from the inner lip contour

Cued Speech (CS) is a manual code that complements lipreading to enhance speech perception from visual input. The phonetic translation of CS gestures needs to combine the manual CS information with information from the lips, taking into account the desynchronization delay (Attina et al. [1], Aboutabit et al. [2]) between these two flows of information. This paper focuses on the analysis of the lip flow for vowels in French Cued Speech. The vocalic lip targets are defined automatically at the instant of minimum velocity of the inner lip contour area parameter, constrained by the corresponding acoustic labeling. We discuss in particular the possibility of discriminating the vowels with geometric lip parameters using the values at the instant of vocalic targets when associated to a Cued Speech hand position.