Cyberpunk In Reality: An Implant That Turns Brain Impulses Into Text

The technology still needs to be refined, but now it can simplify many people around the world.

Scientists from the University of California in the journal The New England Journal of Medicine said that they managed to create a brain implant that can convert neuro impulses of the brain into text with an accuracy of up to 93%. The project authors admitted that they worked on this device for ten years, creating various prototypes of their invention. Still, all previous solutions showed very mediocre results – it was almost impossible to make out the speech. Now they have managed to create a device that will allow people with disabilities to calmly “speak.”

To create the implant, the researchers made a full-fledged map of the brain activity of a healthy person, comparing neural impulses with the sounds spoken by a person, thanks to which words and phrases are formed. After that, the latest development was tested on a 30-year-old patient with complete paralysis, whose brain stem collapsed due to a severe stroke. Before the implant was placed, a person could only enter words by letter using a laser pointer on the visor of his cap, pressing on the on-screen keyboard. A special matrix with electrodes was installed in the brain area through surgery, which is responsible for the vocal muscles during the conversation.

Further, the matrix installed in the brain read the neural impulses of the brain, sending them to a computer, where the neural network compared the information received with a pre-compiled map, converting the impulses into words. At the moment, scientists report a fairly high accuracy of recognition of words and whole phrases (93%), which is noticeably better than all previous prototypes. But, unfortunately, the rate of conversion of impulses into words is still very low – 18 words per minute at an average rate of a healthy person 150-200 words per minute. So researchers still have room to grow and develop, but already now, the technology looks encouraging.

Gray
[ajax_load_more loading_style="infinite classic" single_post="true" single_post_order="previous" post_type="post" elementor="true"]