It marks the first time speech and facial expressions have been captured from brain signals and communicated by an avatar that speaks with the patient’s own voice.

That’s according to Kaylo Littlejohn, a fourth year doctoral student with the University of California San Francisco’s Department of Neurological Surgery, and a lead author on a paper detailing the project, published Wednesday in the journal Nature.

“It is now possible to imagine a future where we can restore fluid conversation to someone with paralysis, enabling them to freely say whatever they want to say with an accuracy high enough to be understood reliably,” Francis Willett, a neuroscientist at Stanford University in California who worked on a similar project, said in a Tuesday press conference, Nature reported.

The patient—a 47-year-old woman named Ann who had experienced a brainstem stroke 18 years ago, preventing her from speaking—agreed to have a paper-thin, credit card-sized set of 253 electrodes surgically implanted onto the surface of her brain, over an area critical for speech. The stroke prevented the signals from moving her tongue, jaw, larynx, and face to create speech and facial expressions.

Ann worked with Littlejohn’s team to train an artificial intelligence-powered system to recognize her brain’s unique signals for speech. That entailed her repeating a variety of phrases from a 1,024-word conversational vocabulary. Once the system was trained, her messages were conveyed by an avatar that used her own voice—reconstructed from a video from her wedding years ago.

Littlejohn was there the first time Ann used the system to speak with her husband. Aside from a computerized device that allows her to use movements in her neck muscles to communicate in a very limited sense, it was the first time she had spoken with her husband in nearly two decades—in a reconstruction of her own voice, no less.

“It was just very heart-warming and encouraging, for both her and me,” Littlejohn tellsFortune. 

For Ann, “it was an emotional experience to hear her own voice,” he adds.

Dr. Edward Chang, chair of neurosurgery at the university, hopes to soon develop a system approved by the U.S. Food and Drug Administration for use by similar patients on a continuous basis.
“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 in a news release about the study. “These advancements bring us much closer to making this a real solution for patients.”