Published On: Wed, Apr 24th, 2019

WSJ: Scientists Use AI to Create Speech From Brain Signals

Neuroscientists have designed a groundbreaking device that utilizes artificial intelligence technology to transform brain signals into speech for people who cannot talk, according to findings published in the Journal Nature.

The Wall Street Journal first reported the research, which focused on five people who had electrodes implanted on the surface of their brains as part of epilepsy treatment. The team at the University of California, San Francisco, recorded brain activity as the participants read sentences out loud, then combined it with data from previous experiments where brain signals that control the movements of the tongue, lips, jaw, and larynx were recorded.

They then trained an algorithm to translate the signals into muscle movements and then, speech sounds.

The decoder improved with more data.

Researchers say the device is not ready to be used outside of the lab.

“Our plan was to make essentially an artificial vocal tract — a computer one — so that paralyzed people could use their brains to animate it to get speech out,” UCSF neurosurgery researcher Gopala K. Anumanchipalli, lead author of the study, told the Journal.

Let’s block ads! (Why?)

Newsmax – Science and Technology

Leave a comment

WSJ: Scientists Use AI to Create Speech From Brain Signals