Lip reading is hardly a new form of communication: it is a primary tool of the deaf community, not to mention a useful skill for transmitting messages across a loud party or over the heads of children. A new form of technology, however, is attempting to mechanize this age-old method of communication. Automatic lip reading, also known as automatic speech reading, is a growing branch of speech recognition technology. In theory, by monitoring a speaker's lip movements and other related elements, specially designed computer programs can interpret verbal messages even when noise interference or other obstacles prohibit a human voice from being properly heard.
Usually, automatic lip reading requires a video of the speaker. The shapes and rhythms formed by the lips are often the most important factors in interpretation, but a variety of other movements can help to decipher the speaker's message, as well. Facial expressions and movements of the head can be determining factors. If any useful audio is available, the automatic lip reading process is significantly facilitated, because context clues from the audible portion can suggest inaudible words or fragments of speech.
The development of automatic lip reading technology rests on the ability to identify isolated words that use the same lip movements every time they are spoken. Lip Geometry Estimation (LGE) is one of the more advanced computer systems in place that monitors and interprets such patterns. Scientists have developed a notable automatic lip reading and speech recognition system for the Dutch language, but in general, the field still has plenty of room for progress.
Automatic lip reading has received a recent surge of interest and attention due to its implementation on archived home videos of Adolf Hitler. Filmed by Eva Braun during the war, the once-silent films came to life when speech recognition technology was applied to the footage. Whether or not the interpretations are entirely accurate, the automatic lip reading program has provided a glimpse into a historical figure that will no doubt create continued interest in the field of automatic lip reading.
