A new device has been developed that can analyze the brain waves of paralyzed patients and convert them into sentences on a computer screen in real time.
The mind-reading machine is able to decipher brain activity as a person silently tries to spell words phonetically to form complete sentences.
Experts say that the neuroprosthesis is able to restore communication with people who cannot speak or write due to paralysis.
Previous studies have shown that a similar system can decode up to 50 words.
However, this was limited to a certain vocabulary and the participant had to try to say the words out loud, which required considerable effort given their paralysis.
So Edward Chang and his colleagues at the University of California have developed a neurosuit capable of translating brain activity into single letters to form whole sentences in real time.
It was then demonstrated in a human subject with limited contact due to severe voice and limb paralysis.
The researchers extended the previous approach to a wider vocabulary by developing their system for decoding brain activity associated with the phonemic alphabet.
In tests, the device was able to decode the brain activity of volunteers as they tried to pronounce each letter phonetically without words to form sentences from 1,152 dictionary words at a rate of 29.4 letters per minute and an average writing error rate of 6.13 percent.
In other experiments, the researchers found that the approach was extended to a large vocabulary of over 9,000 words, with an average error rate of 8.23%.
They say the results demonstrate the ability of silently controlled neural prostheses to create sentences with a spelling-based approach using audio-encoded words.
Successfully transcribed sentences include “Good morning”, “You must be joking”, “What do you mean”, “I think it’s very good”, and “I’ll check”.
But despite the device’s success, the researchers caution that more work is needed to prove whether this approach can be successfully used in more participants.
“These results demonstrate the clinical feasibility of silence-controlled speech-specific neural compensation for generating sentences from a large vocabulary using a spelling-based approach, complementing previous demonstrations of direct decoding of whole words,” the researchers write in their paper.
Details about the new device were published in the magazine Connection with nature.
Source: Daily Mail