Visual speech synthesis using statistical models of shape and appearance

B Theobald, JA Bangham, I Matthews, GC Cawley

Research output: Contribution to conferencePaper

8 Citations (Scopus)


In this paper we present preliminary results of work towards a video-realistic visual speech synthesizer based on statistical models of shape and appearance. A sequence of images corresponding to an utterance is formed by concatenation of synthesis units (in this case triphones) from a pre-recorded inventory. Initial work has concentrated on a compact representation of human faces, accommodating an extensive visual speech corpus without incurring excessive storage costs. The minimal set of control parameters of a combined appearance model is selected according to formal subjective testing. We also present two methods used to build statistical models that account for the perceptually important regions of the face.
Original languageEnglish
Number of pages6
Publication statusPublished - Sep 2001
EventInternational Conference on Auditory-Visual Speech Processing (AVSP-2001) - Aalborg, Denmark
Duration: 7 Sep 20019 Sep 2001


ConferenceInternational Conference on Auditory-Visual Speech Processing (AVSP-2001)

Cite this