Researchers from University of East Anglia are using an automated lip reading system to improve the ability of deaf people to communicate effectively. Findings of the study are being presented at the International Conference on Auditory-Visual Speech Processing (AVSP) 2009 this week at UEA. The computerized system was shown to have a much higher word recognition ability than the human control group of 19 subjects, leading to the implication that mobile electronic lip readers may become available in the not too distant future.
Furthermore, they found that machines are able to exploit very simplistic features that represent only the shape of the face, whereas human lip-readers require full video of people speaking.
The study also showed that rather than the traditional approach to lip-reading training, in which viewers are taught to spot key lip-shapes from static (often drawn) images, the dynamics and the full appearance of speech gestures are very important.
Using a new video-based training system, viewers with very limited training significantly improved their ability to lip-read monosyllabic words, which in itself is a very difficult task. It is hoped this research might lead to novel methods of lip-reading training for the deaf and hard of hearing.
“This pilot study is the first time an automated lip-reading system has been benchmarked against human lip-readers and the results are perhaps surprising,” said the study’s lead author Sarah Hilder.
“With just four hours of training it helped them improve their lip-reading skills markedly. We hope this research will represent a real technological advance for the deaf community.”
Full story: A new study by the University of East Anglia suggests computers are now better at lip-reading than humans…