A research team at the Massachusetts Institute of Technology has developed a device that can listen to and transcribe a person’s otherwise silent inner voice, to make that information available to record or transmit electronically–all without the user having to utter a word.
The device, called "AlterEgo" by its designers, makes use of a specialized headset that wraps around the back of the user’s ear, with an extension placed along the jawline. It picks up on neuromuscular signals transmitted through the jaw and face, an unconscious result of the internal verbalizations being made by the individual. These signals are then interpreted by a machine-learning system that translates the patterns into words.
Additionally, the device employs a pair of bone-conduction headphones that can transmit vibrations to the wearer’s inner ear, to allow them to listen to information without the obstruction of wearing earphones.
"The motivation for this was to build an IA device — an intelligence-augmentation device," explains Arnav Kapur, a graduate student at the MIT Media Lab, and head of the team that developed AlterEgo. "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?"
While investigating this concept, Kapur’s team found that most of the useable neuromuscular signals came from just four points on a person’s face, allowing them to pack the sensors into a comparatively compact headset. The device needs to be trained to recognize each individuals’ internal speech patterns, but it can do so fairly quickly: the prototype currently can reach a 92 percent accuracy in its transcriptions after just 90 minutes of training. Kapur expects that the AI’s accuracy will improve as more data becomes available to it to learn from.
A device that can pick up on a person’s inner-voice has a wide range of applications: It could enable people with medical conditions that cause vocal difficulties to speak clearly, such as how Stephen Hawking’s machine allowed him to communicate; people working in noisy environments where being heard is difficult, such as airport tarmacs, could benefit from such a device; and it could provide an additional layer of safety in situations where speaking could be downright dangerous, such as to soldiers on spec-ops missions.
But a device like AlterEgo could also address problems that are endemic to our regular day-to-day communications devices. As MIT media arts and sciences professor Pattie Maes explains, "We basically can’t live without our cellphones, our digital devices. But at the moment, the use of those devices is very disruptive. If I want to look something up that’s relevant to a conversation I’m having, I have to find my phone and type in the passcode and open an app and type in some search keyword, and the whole thing requires that I completely shift attention from my environment and the people that I’m with to the phone itself. So, my students and I have for a very long time been experimenting with new form factors and new types of experience that enable people to still benefit from all the wonderful knowledge and services that these devices give us, but do it in a way that lets them remain in the present."
Subscribers, to watch the subscriber version of the video, first log in then click on Dreamland Subscriber-Only Video Podcast link.