The new technology works by electrodes being fitted to the face and jaw of the user, designed to pick up otherwise undetectable neuromuscular signals. These slight muscle movements are triggered by internal verbalizations, that is when a person thinks what they are saying rather than actually verbalizing. When a person says words'in their head' any muscle movement cannot be seen with the human eye. It is, as the new research demonstrates, possible to detect this with the aid of artificial intelligence. The technology comes from the Massachusetts Institute of Technology, and it uses machine-learning system to correlate particular signals with particular words.

"I think that they're a little underselling what I think is a real potential for the work," says Thad Starner, a professor in Georgia Tech's College of Computing. "Like, say, controlling the airplanes on the tarmac at Hartsfield Airport here in Atlanta. You've got jet noise all around you, you're wearing these big ear-protection things -- wouldn't it be great to communicate with voice in an environment where you normally wouldn't be able to? You can imagine all these situations where you have a high-noise environment, like the flight deck of an aircraft carrier, or even places with a lot of machinery, like a power plant or a printing press. This is a system that would make sense, especially because oftentimes in these types of or situations people are already wearing protective gear.