A lip-reading system that converts videos of conversations into written transcripts is being developed by researchers from the University of East Anglia's (UEA's) School of Computing Sciences and Surrey University.

Funded by England's Engineering and Physical Sciences Research Council (EPSRC), it is hoped the research will be used to develop a system for the deaf to dictate commands to computers in noisy environments.

Dr Richard Harvey, a Professor at UEA hopes a prototype will emerge within two years.

"To be effective the systems must accurately track the head over a variety of poses, extract numbers or features that describe the lips, and then learn what features correspond to what text," explained Harvey.

Software to track face and lip movements has already been developed, and the team is now working on building a library of videos in order to create a database of facial expressions and lip movements used for each letter combination.