Friday , February 26 2021

Scientists say their AI can read what's happening in the brain – RT World News

Neuroinjectors at the University of Columbia in New York state that they have created a system that can translate human thoughts into a recognizable speech that would revolutionize not only medicine but communication.

Following the brain activity of the subjects, researchers from the Mental Behavior Institute of Mortimer B. Zuckerman of Columbia were able to train artificial intelligence to translate patterns of thought into intelligible sentences, according to a document Published on Tuesday in the journal Scientific Reports. The authors see patients with problems of disability due to illnesses or traumas as early adopters of the incipient technology.

"We have shown that, with the right technology, the thoughts of these people could be decoded and understood by any listener." said Dr. Nima Mesgarani, the lead author of the document.

After the first attempts by researchers to translate brain activity into a recognizable speech failed, they went to a computer algorithm that could generate a speech called vocoder. The algorithm improves the most "Format" for recordings of human speech.

"This is the same technology that Amazon Echo and Apple Siri use to give verbal answers to our questions." said Dr. Mesgarani, who is also a professor at the Columbia Fu Foundation School of Engineering and Applied Sciences.

The vocoder was trained to interpret the brain activity with the help of Dr. Ashesh Dinesh Mehta, neurosurgeon at the Northwell Health Neuroscience Institute in Long Island, and co-author of the paper.

"Working with Dr. Mehta, we asked patients with epilepsy who were already undergoing brain surgery to hear phrases spoken by different people, while we measured patterns of brain activity." said Dr. Mesgarani. "These neuronal patterns formed the vocoder".

After this training, the following phase was started. Patients listened to a person reading numbers from 0 to 9, while the algorithm scanned the brain's activity and tried to translate it into sound. The result was a robotic voice reading number, which human listeners could understand and repeat with a precision of 75%.

This may seem quite modest, but Dr. Mesgarani said that such a result is "Beyond previous attempts". The researchers plan to further improve the system, so that it can be taken as a brain entry pattern of a person who thinks about the speech, not listening to it.

"This would be a game changer. It would give anyone who has lost their ability to speak, either by injury or illness, with the possibility renewed of connecting to the world that surrounds them" Mesgarani said.

Technology will also have to work with more complex words and phrases to be more practical. The ultimate goal of the team is to create an implant that synthesizes the discourse directly from the thought.

Do you think your friends would be interested? Share this story!

Source link