Skip to main content

New Brain Implant Transmits Full Words from Neural Signals

No spelling out of letters is needed for a paralyzed person to use the first-of-a-kind neuroprosthesis

Neurosurgeon Edward Chang in full surgical garb.

Neurosurgeon Edward Chang, who performed the neuroprosthetic surgery.

Barbara Ries

More than 15 years ago, a man who was only 20 years old had a massive stroke when a major artery supplying his brain stem burst. The incident left him unable to control his limbs or any muscles related to speech. With a device that relied on his head motions to control a keyboard, he could produce about five words a minute, one character at a time. The typical rate when someone is speaking fluidly can be up to 200 words a minute.

Now he is the first person ever to produce whole words via a computer intermediate that decodes his brain’s messages. A processor connected to an array of electrodes implanted in his brain receives the messages and translates them into words displayed on a screen. As researchers reported on July 14 in the New England Journal of Medicine, the man, who is now in his late 30s, used this brain-computer interface, or BCI, to produce whole words outside of his brain for the first time since his stroke. In fact, with a suite of at least 50 words, he could even transmit up to 1,000 complete sentences.

Earlier generations of neuroprostheses have relied on communications from the brain to the limb or hand muscles to activate letters on a keyboard. Messages are relayed around the unresponsive muscles to a processor that translates them into single-letter keystrokes. As with using head movements, word production is slow and tedious and often produces just a few words a minute. Now researchers have decoded the origin of brain signals controlling speech and created the new neuroprosthesis that facilitates the production of whole words, yielding a faster word-per-minute rate.


On supporting science journalism

If you're enjoying this article, consider supporting our award-winning journalism by subscribing. By purchasing a subscription you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.


“This is a big step, one big step among many that we’ll be able to take,” says Vikash Gilja, an associate professor of electrical and computer engineering at the University of California, San Diego, who was not involved in the study. A key advance, he says, is the “incredible proof of concept” that someone who has been unable to speak for more than a decade and a half can still generate speech signals to use with these interfaces.

“This was not like an overnight kind of thing, where we just plugged it in,” says the study’s senior author Edward Chang, chair of neurosurgery at the University of California, San Francisco. He and his colleagues first spent many years sorting out how the brain controls speech-related muscles, pinpointing the messages and movements associated with each vowel and consonant in the English alphabet. When they launched the BCI Restoration of Arm and Voice (BRAVO) study to test the 128-electrode brain implant they had developed, the first participant was the man who had suffered a stroke at age 20, who goes by the pseudonym “Bravo-1.”

He worked through 50 sessions of a half hour or so each during 81 weeks of the study. In the sessions, researchers would present a target word or sentence on a screen. When Bravo-1 engaged his brain to send the related speech signals, the processor picked them up through the implanted electrodes and transmitted their message to a computer. The computer side of the device decoded Bravo-1’s messages correctly 74.5 percent of the time (logging more than 90 percent accuracy occasionally)—and it produced a median rate of about 15.2 words per minute.

That is, of course, nowhere near the fluidity of a fast-talking teenager. Achieving better performance and accurate message decoding will require combining the high accuracy of devices that signal through the upper limb and this “critical demonstration that the speech signals are present and that they can be leveraged,” Gilja says.

Chang says that for his group, the next steps are to see “if this is better, worse or the same in more people” while the researchers also use a larger vocabulary to train the machine that decodes the brain’s output. The vocabulary has already expanded beyond the 50 words reported in this study, he says, and “it’s exciting to see things grow in that kind of way.”

When asked about how Bravo-1 responded to the success he’s experienced so far, Chang says, “I think he was really thrilled and excited, and this is really just the beginning.”

Emily Willingham is a science writer and author of the books Phallacy: Life Lessons from the Animal Penis (Avery, Penguin Publishing Group, 2020) and The Tailored Brain: From Ketamine, to Keto, to Companionship: A User's Guide to Feeling Better and Thinking Smarter (Basic Books, 2021).

More by Emily Willingham
SA Mind Vol 32 Issue 5This article was originally published with the title “New Brain Implant Transmits Full Words from Neural Signals” in SA Mind Vol. 32 No. 5 (), p. 15
doi:10.1038/scientificamericanmind0921-15