A severely paralyzed person has been able to communicate using a new type of technology that can directly convert signals from the brain into sounds that appear on the screen.Developed by researchers University of California, San Francisco, For people with aphasia, this technology is a more natural way of communication than other methods We have seen So far.
So far, neuroprosthetic technology has only allowed paralyzed users to enter only one letter at a time, a process that can be slow and laborious. It also digs into the part of the brain that controls the arm or hand. This system is not necessarily intuitive to the subject.
However, the USCF system uses an implant that is placed directly on the part of the brain dedicated to speech. In this way, subjects can mentally activate their brain patterns that they usually use to say a word, and the system can translate entire words instead of individual letters to the screen.
To make it work, patients with normal speech voluntarily analyze their brain recordings to understand speech-related activities. Researchers can then analyze these patterns and develop new methods to decode them in real time, using statistical language models to improve accuracy.
However, the team is still unsure whether the brain signals that control the vocal tract remain intact in patients who have been paralyzed for many years. To this end, they recruited an anonymous participant (called Bravo1), who worked with researchers to create a 50-word vocabulary that the team could use advanced computer algorithms to decipher. These include words such as “water”, “family” and “good”, enough for patients to create hundreds of sentences applicable to their daily lives. The team also used an “auto-correction” feature similar to that in consumer voice recognition applications.
To test the system, the team asked the patient Bravo1 to answer questions such as “How are you today?” And “Do you want some water?” The patient’s attempted speech then appeared on the screen, such as “I’m fine” and “No, I’m not thirsty”.
The system can decode their speech at a speed of up to 18 words per minute, with an accuracy of 93% and a median accuracy of 75%.Compared to normal speech with 200 words per minute, this may not sound very good, but it is much faster than the speed seen above Previous neuroprosthetic system.
Edward Chang, MD, director of neurosurgery at the University of California, San Francisco and senior author of the study, said: “As far as we know, this is the first successful demonstration of decoding complete words directly from the brain activity of a paralyzed and unable to speak. Demonstration.” “It shows the powerful prospect of restoring communication by using the brain’s natural language mechanisms.”
The team said that the test proved the principle of this new type of “speech neuroprosthesis.” Next, they plan to expand the scope of the experiment to include more participants, while also working to increase the number of words in the vocabulary and increase the speed of speech.
All products recommended by Engadget are selected by our editorial team, independent of our parent company. Some of our stories include affiliate links. If you purchase goods through one of these links, we may earn member commissions.