Reading lips is a skill usually reserved for fictional spies or the hearing impaired, but researchers have spent years trying to gift the talent to computers, too. However lately, researchers have said that lip reading is still too hard for computers.
Ahmad Hassanat, a researcher at Mu’Tah University in Jordan has mentioned that we have a long way to go before machine eyes can tell what we’re saying. According to Hassanat, human speech uses more than 50 distinct sounds to form words and syllables, but the mouth itself only forms between 10 and 14 distinguishable shapes.
Lip reading is not just simply recognizing and putting together the sounds those shapes represent; rather it’s partially a guesswork. To suss out exactly what sounds a speaker is making, lip readers have to take in body language, facial expressions and the context of the conversation to help them decipher words.
A device like computer capable of automated lip-reading would certainly be a game changer. Although Hassanat’s own experiments have produced an average success of 76-percent in lip reading, he has said that “we still have a long way to go” and we have major hurdles to leap before we can expect machines to decode lip movements. You can read his write up for yourself from the source link given below.