Check It Out – New Headset Enables You To Talk Without Using Your Mouth

Researchers from the Massachusetts Institute of Technology have created a headset called AlterEgo.

Amazingly, the headset can transcribe your thoughts, we saw a similar idea and concept from an episode of Black Mirror but now it’s in reality’s fruition.

The new device is supposed to be worn on the face, and electrodes pick up signals from your jaw and face that are triggered by internal thoughts but are undetectable to the human eye.

These signals picked up by the electrodes are then fed to a machine – learning system that’s trained to associate certain signals with certain words. The system also contains a pair of bone -conduction headphones, which transmit vibrations through the bones of the face to the inner ear.

This enables the system to carry out information to the user without interrupting their conversation.

Professor Pattie Maes, who supervised on the study, said :

“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.”

To develop properly the efficiency of the AlterEgo device, the researchers first had to determine which parts of the face are the sources of the reliable neuromuscular signals.

To do this, they conducted a survey and asked several people to say a series of words, while wearing a range of electrodes on their face.

This allowed them to distinguish where on the face different sounds are vocalised.

The resulting headset is around 92 percent accurate, but the researchers believe that this should improve with more training data.

Worth sharing?

Please share on Facebook or Twitter. It helps more people see it.