The neuro-engineers at the University of Columbia, in New York, USA, have created a system that translates thought into a comprehensible and recognizable discourse, which can mean new ways for computers to communicate directly with the brain.
By monitoring someone's brain activity, technology can recreate words that people can hear with unprecedented clarity.
This advancement, which accentuates the power of voice synthesizers and artificial intelligence, sets the basis for people who can not speak, such as those who live with Amyotrophic lateral sclerosis (ELA) or recover from stroke, restored the ability to communicate with the outside world.
"Our voice helps us to connect with our friends, family and the world around us so that loss of voice due to injury or illness is so catastrophic," said Nima Meshargani, chief researcher at the Institute for Mental Behavior. Cerebral Mortimer B. Zuckerman from the University of Columbia.
The expert thought that they showed that "with appropriate technology, the thoughts of these people can be deciphered and understood by any other listener."
Models in the brain
Decades of research have shown that when people talk and even imagine themselves talking, discovering patterns of activity appears in their brain.
Another pattern of signals also appears when we hear someone talking or imagining that we are listening.
The team of researchers turned to "vocoder," a computerized algorithm that can synthesize the words after receiving training to capture people who speak.
"This is the same technology used by Amazon Echo and Siri from Apple, which gives verbal answers to our questions," Mesgarani explained.
To teach a "vocoder" for the interpretation of brain activity, Meggary teamed up with Annes Dinesh Mehta, a neurosurgeon at the Northwell Institute for Health Neurone Partners, who treats patients with epilepsy, some of whom must undergo regular operation the brain.
"Working with Dr. Mehta, we asked epileptic patients who had already undergone brain surgery to hear the phrases spoken by different people while measuring the patterns of brain activity," said Mersani, who stressed that these neuronal models train "vocoder"
The team plans to test the most complicated words and phrases later and even strives to have their system part of an implant similar to those used in some patients with epilepsy who translate the user's thoughts directly into words.
"This will give someone who has lost the ability to speak, whether due to injury or illness, a new opportunity to connect with the world," he added. EFE