Auditory-Visual Speech Processing
Our goal is to create a natural Italian talking face with, in particular, lip-readable movements. Based on real data extracted from an Italian speaker with the ELITE system, we have approximated the data using radial basis functions. In this paper we present our 3D facial model based on MPEG-4 standard and our computational model of lip movements for Italian. Our experiment is based on some phonetic-phonological considerations on the parameters defining labial orifice, and on identification tests of visual articulatory movements.
Bibliographic reference. Pelachaud, C. / Magno-Caldognetto, E. / Zmarich, C. / Cosi, P. (2001): "Modelling an Italian talking head ", In AVSP-2001, 72-77.
|av01_072_1.avi (105 KB)||pelachaud-small-aba-ntsc.avi|
|av01_072_2.avi (105 KB)||pelachaud-small-ada-ntsc.avi|
|av01_072_3.avi (105 KB)||pelachaud-small-aga-ntsc.avi|
|av01_072_4.avi (105 KB)||pelachaud-small-ava-ntsc.avi|