AI helps paralyzed woman ‘speak’ for first time in years using copy of her recorded voice

Artificial intelligence technology is helping a woman “speak” for the first time in years after she suffered a stroke that left her paralyzed and unable to talk.

Ann Johnson, 48, suffered a stroke in 2005 at the age of 30. Since then, she has been unable to talk.

“Not being able to hug and kiss my children hurt so bad, but it was my reality,” Johnson stated. “The real nail in the coffin was being told I couldn’t have more children.”

Experimental AI technology developed by researchers at the University of California, Berkeley, and the University of California, San Francisco, has allowed Johnson to communicate once again.

The technology relies on an implant containing 253 electrodes located in the region of the brain associated with speech and language. Johnson’s brain signals are translated into audible works through a digital avatar capable of blinking and using facial expressions.

“The device is an electrocorticography grid which is attached to a pedestal, which is screwed onto the participant’s skull,” said Margaret Seaton, a clinical research coordinator at USSF.

Johnson’s digital avatar uses a copy of her recorded voice from a toast she gave at her wedding years ago.

In order to use the AI system, it first had to be trained to associate certain brain signals with various sounds. To do this, Johnson had to silently and repeatedly recite phrases from a 1,024-word vocabulary.

The AI technology is not trained to recognize entire words. Instead, it is taught to identify 39 phonemes that it then uses to complete words. It is capable of generating 80 words per minute, which is approximately half of the average rate of dialogue.

Sean Metzger, who developed the text decoder, emphasized that it is essential for the program to be accurate and fast.

“It’s what gives a user the potential, in time, to communicate almost as fast as we do, and to have much more naturalistic and normal conversations,” Metzger stated.

Dr. Edward Chang, the neurological surgery chairman at UCSF, hopes the program will lead to FDA approval in the near future.

“Our goal is to restore a full, embodied way of communicating, which is really the most natural way for us to talk with others,” Chang said. “These advancements bring us much closer to making this a real solution for patients."

The researchers are now working on a wireless version of the program.

Artificial Intelligence helps woman speak after 18 years without a voiceyoutu.be

Like Blaze News? Bypass the censors, sign up for our newsletters, and get stories like this direct to your inbox. Sign up here!