Towards video realistic synthetic visual speech

B Theobald, JA Bangham, I Matthews, GC Cawley

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

In this paper we present initial work towards a video-realistic visual speech synthesiser based on statistical models of shape and appearance. A synthesised image sequence corresponding to an utterance is formed by concatenation of synthesis units (in this case phonemes) from a pre-recorded corpus of training data. A smoothing spline is applied to the concatenated parameters to ensure smooth transitions between frames and the resultant parameters applied to the model—early results look promising.
Original languageEnglish
Pages3892-3895
Number of pages4
DOIs
Publication statusPublished - May 2002
EventIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP- 2002) - Orlando, Florida
Duration: 13 May 200217 May 2002

Conference

ConferenceIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP- 2002)
CityOrlando, Florida
Period13/05/0217/05/02

Cite this