MIT figures out how to silently communicate
MIT does it again...
Researchers at MIT have developed a headset, called AlterEgo, that allows you to communicate by simply "speaking silently" to yourself. The team was led by Arnav Kapur who says users can be walking down the street and without saying a word or doing anything noticeable to the human eye can be communicating with a computer. Keep in mind the headset isn't necessarily reading your mind. Instead, it uses electrodes to read the neuromuscular signals from the user's internal speech organs when they "say" words in their head. Basically, using bone conduction the headset is aware of the user's jaw muscles that allow for soundless communication. The headset has been trained to be able to associate certain transmissions with specific words - currently - the headset can accurately decipher 100 words but the team intends on adding many more. "Our idea was: Could we have a computing platform that's more internal, that melds human and machine in some ways and that feels like an internal extension of our own cognition," says Kapur.
What's the point?
A professor at Georgia Tech, Thad Starner, put this technology into practice and mentioned how beneficial it would be for those directing airplanes. “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.” Not to mention technology like this can be very valuable for special operations where speaking can potentially mean being detected by your enemy. Or even giving voice to those that can't speak - like individuals who have suffered a stroke and are regaining their speech.
Where is the tech now?
Currently, AlterEgo has been used to communicate with the streaming service Roku. Users could silently navigate the Roku interface to decide what they wanted to watch. AlterEgo has also been used to play a game of chess. Used in arithmetic situations the device has performed relatively well with a 92% accuracy rate across a 10 person trial.