Home / Health / Brain speech signals transformed into written text in seminal research for people with paralysis

Brain speech signals transformed into written text in seminal research for people with paralysis

In a research project, physicians were able to transform brain signals for speech into written sentences to change how patients communicate with severe disabilities.

Breakthrough is said to be the first to show how the intention to pronounce certain words can be extracted from brain activity and quickly converted into text.

According to The Guardian, the brain reading software only works with certain sets that can be trained, though scientists believe that a more powerful system could be built in the future.

Physicians at the University of California hoped to develop a product that would make it easier for people with paralysis to communicate than with existing devices that record eye movements and muscle twitches to control a virtual keyboard.


FOR BIG TECH, GREAT FINEES CREATE LIMITED DAMAGE ONLY [19659003] "To date, there is no voice prosthetic system that allows users to perform interactions on the fast time scale of a human conversation can, "said Edward Chang, neurosurgeon and senior researcher in the study.

Three Epilepsy Patients on the Rise According to the researchers, neurosurgery placed a tiny spot of electrodes directly on the brain for a week to determine the causes of their seizures.

Chang's patients at the hospital reportedly allowed her seizures to record brain activity, while each was asked nine questions and asked to read a list of 24 possible answers. Chang's team then built computer models that reconciled brain activity patterns with questions and answers.

"This is the first time spoken words and phrases have been identified with this approach," said David Moses, a researcher for the team, the Guardian said. "It is important to remember that we have achieved this with a very limited vocabulary, but we hope that in future studies we can increase the flexibility and accuracy of what we translate."

Journal published Nature and the work itself were funded by Facebook.


Source link