New headset lets you interact with computers using your mind

Kyle Chua

This is AI generated summarization, which may have errors. For context, always refer to the full article.

New headset lets you interact with computers using your mind
Electrodes on the device recognize neuromuscular signals in the face and jaw that are triggered by saying words in your head

MANILA, Philippines – A group of MIT researchers have developed a computer interface called AlterEgo that lets its users interact with computers using their internal voices. It consists of a wearable headset that runs along the user’s ear to the side of the mouth and a computing system.

The researchers discovered that internal verbalizations physically send out subtle signals to a number of locations in the face. These signals are picked up by the electrodes on the device and fed to a machine learning system that associates them with the corresponding words or actions.

“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 Arnav Kapur, a graduate student at the MIT Media Lab, who led the development of the project.

In addition, the researchers included a unique kind of headphones to emit sound. The device transmits vibrations from the face to the ear, meaning the user’s normal hearing would not be interrupted.

Kapur and his team wanted to create an interface that offered the same services as a smartphone, only much less disruptive. Their tests show that even with just 20 words in its vocabulary the device is capable of performing numerous tasks including navigating a set-top box without the need for verbal commands or physical button presses.

In its current state, the researchers said it achieves a 92% accuracy rating which is to improve in time when the system gathers more data with each use. “We’re in the middle of collecting data, and the results look nice,” Kapur says. “I think we’ll achieve full conversation some day.”

On top of this, the researchers are working on finding the most reliable locations in the face that send out neuromuscular signals to lessen the sensors needed and make it less intrusive to wear.

They hope their device can one day help those with speaking disabilities or be beneficial to those working in high-noise environments such as power plants, printing presses, and airport tarmacs. – Rappler.com

Add a comment

Sort by

There are no comments yet. Add your comment to start the conversation.

Summarize this article with AI

How does this make you feel?

Loading
Download the Rappler App!