Research scientists at the University of East Anglia found lip-reading computers significantly outperformed human lip-readers, scoring a recognition rate of 80 per cent, compared with 32 per cent for human viewers on the same task.

The study also suggested methods of improving lip-reading by the deaf and showed that rather than the traditional approach to lip-reading training (viewers are taught to spot key lip shapes from static, often drawn, images), the dynamics and full appearance of speech gestures are very important.