Joint audio-video processing for multimedia
T. Chen, R.R. Rao · 2002
In this paper, the authors report recent developments in the research of joint audio-visual processing for multimedia applications. These include: bimodality in speech production and perception, automatic lipreading, talking-head animation and lip synchronization. They present in detail the enabling technologies for these applications. A new trend of research is to utilize audio-visual interaction in the coding of talking head video. They show that the marriage of speech analysis and image processing can create a number of new research opportunities.