Columbia University's Neuroengineer in New York (USA) has developed a system that converts thoughts into an understandable and recognizable discourse that could mean new ways for computers to communicate directly with the brain.
By observing what the brain is doing, technology can restore words that one can hear with unprecedented clarity.
This progress, using the voice synthesizer and the power of artificial intelligence, is the basis for people who can't speak, for example, those who live with Amyotrophic lateral sclerosis (ELA) or recover from a stroke to recover the ability to communicate with the outside world.
"Our voice helps us communicate with our friends, family, and the world around us, so the loss of voice power due to injuries or illness is so devastating," said Nima Mesgarani, chief researcher at the Institute of Mental Behavior. Brain Mortimer B. Zuckerman of Columbia University.
The expert believed that they had proved that "with the right technology, these people's thoughts can be deciphered and understood by any other listener".
Articles in the brain
Research over decades has shown that when people talk and even imagine that they are talking, patterns of action appear in their brains.
A different pattern of signals also appears when we hear someone speak or imagine that we are listening.
The research team turned to a "vocoder", a computerized algorithm that can synthesize words after they have received training record entries.
"This is the same technology used by Amazon Echo and Siri from Apple, which provides oral answers to our questions," explained Mesgarani.
To teach the "vocoder" to interpret brain activity, Mesgarani collaborated with the Institute of Neurology at Ashesh Dinesh Mehta, a neurology institute for treating patients with epilepsy, some of whom are subject to regular brain surgery.
"When working with Dr. Mehta, we asked patients with epilepsy who had already undergone brain surgery to listen to the expressions of different people measuring brain activity patterns," said Mesgarani, who said these nerve models were trained as "vocoder"
The team plans to examine the most complex words and phrases later and even wants their system to be part of an implant similar to those used in some patients with epilepsy, which directly convert the user's thoughts into words.
"This would give someone who has lost the ability to speak, either by trauma or illness, a new opportunity to communicate with the world," he added. EFE