9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Feature Adaptation of Hearing-Impaired Lip Shapes: The Vowel Case in the Cued Speech Context

Noureddine Aboutabit (1), Denis Beautemps (1), Olivier Mathieu (1), Laurent Besacier (2)

(1) GIPSA, France; (2) LIG, France

The phonetic translation of Cued Speech (CS) gestures needs to mix the manual CS information together with the lips, taking into account the desynchronization delay (Attina et al. [1], Aboutabit et al. [2]) between these two flows of information. This contribution focuses on the lip flow modeling in the case of French vowels. Previously, classification models have been developed for a professional normal-hearing CS speaker (Aboutabit et al., [3]). These models are used as a reference. In this study, we process the case of a deaf CS speaker and discuss the possibilities of classification. The best performance (92.8%) is obtained with the adaptation of the deaf data to the reference models.


  1. Attina, V., Beautemps, D., Cathiard, M. A. and Odisio, M. "A pilot study of temporal organization in cued speech production of French syllables: rules for Cued Speech synthesizer," Speech Communication, 44, pp. 197-214, 2004.
  2. Aboutabit, N., Beautemps, D. and Besacier, L., "Hand and Lips desynchronization analysis in French Cued Speech: Automatic segmentation of Hand flow". In Proc. of ICASSP, 2006.
  3. Aboutabit, N., Beautemps, D. and Besacier, L., "Vowels classification from lips: the Cued Speech production case". In Proceedings of ISSPí06, 2006

Full Paper

Bibliographic reference.  Aboutabit, Noureddine / Beautemps, Denis / Mathieu, Olivier / Besacier, Laurent (2008): "Feature adaptation of hearing-impaired lip shapes: the vowel case in the cued speech context", In INTERSPEECH-2008, 2843-2846.