Saturday , February 27 2021

Engineers in the United States manage to convert brain signals into speech

Newcomers from Columbia University in New York (USA) created a system that translates thoughts into an intelligible and recognizable speech, which could mean new ways for computers to communicate directly with the brain, according to a well-known research this Tuesday.

In order to monitor someone's brain activity, technology can recreate the words a person can hear with unprecedented clarity.

This breakthrough, which takes advantage of the power of speech synthesizers and artificial intelligence, puts the foundation for people who can not speak, such as those who live with amyotrophic lateral sclerosis (ELA) or recover from an accident Stroke, recover the ability to communicate with the outside world.

"Our voice helps us connect with our friends, family and the world around us, so losing the power of the voice because of an injury or illness is so devastating," said Nima Mesgarani, principal investigator at the Mental Health Behavioral Institute Mortimer B. Zuckerman of Columbia University.

The expert considered that they have shown that, "with the right technology, the thoughts of these people can be deciphered and understood by any other listener."

Decades of research have shown that when people speak and even imagine speaking, they appear revealing patterns of activity in their brains.

A different signal pattern also appears when we hear someone talk or imagine that we hear.

The researchers team resorted to a "vocoder", a computer algorithm that can synthesize words after having received training in recordings of people who speak.
"This is the same technology used by Amazon Echo and Siri Apple that gives verbal answers to our questions," explained Mesgarani.

To teach "vocoder" to interpret brain activity, Mesgarani teamed up with Ashesh Dinesh Mehta, a neoregioner at the Northwell Health Physician Partners Neuroscience Institute, who serves patients with epilepsy, some of whom must undergo regularly to cerebral surgical operations.

"Working with Dr. Mehta, we asked epileptic patients who had already undergone brain surgery to hear the phrases spoken by different people as we measured the patterns of brain activity," said Mesgarani, who pointed out That these neural patterns train the "vocoder".

The team plans to try the most complicated words and phrases later and even aspires to have a system part of an implant similar to those used with some patients with epilepsy that translate the thoughts of the user directly in words.

"This would give someone who has lost their ability to speak, either by injury or illness, a new opportunity to connect with the world," he added.

Source link