“Hearst Magazines and Yahoo may earn commission or revenue on some items through these links.”
Here’s what you’ll learn when you read this story:
Many people around the world, especially those with neurodegenerative diseases, have lost the ability to communicate effectively.
A developing technique—leveraging a brain-computer interface (BCI) and an AI-powered decoder—could help give a voice to the voiceless by accurately interpreting neural activity in the brain’s motor cortex.
Future hardware improvements and exploration into other regions of the brain will likely improve this mind-reading tech.
For the past few years, Stanford’s Neural Prosthetics Translational Laboratory, led by co-director Frank Willett, has made the habit of translating the untranslatable.
In 2021, the laboratory revealed a brain-computer interface (BCI) capable of translating the thoughts of attempted handwriting (in those suffering from motor disabilities) into speech by analyzing the neural activity in the motor cortex. Two years later, the same laboratory demonstrated a similar feat with a BCI that translated attempted speech. Now, seemingly like clockwork, the Stanford lab has pushed things yet another step further, eschewing the need for attempted handwriting and speech and instead analyzing the neural activity of the inner monologue directly. The results of this final installment of this (unofficial) BCI trilogy was published last week in the journal Cell.
“For people with paralysis, attempting to speak can be slow and fatiguing, and if the paralysis is partial, it can produce distracting sounds and breath control difficulties,” Willett, a co-author on all three studies (including the latest one), said in a press statement. “We wanted to know whether a BCI could work based only on neural activity evoked by imagined speech, as opposed to attempts to physically produce speech.”
To translate this world of imagined speech, Willett and his team relied on four participants in the Brain2Gate trial—a study initially designed for developing proof-of-principle for people with tetraplegia to control computer cursors and other assistive devices with their thoughts alone. The study analyzed neural activity of the motor cortex using multiple 64-channel microelectrode arrays originally implanted in the participants’ brains for the previous trial. At least two of the volunteers (a 68-year-old woman and a 33-year-old man) were diagnosed with ALS, and either couldn’t intelligibly communicate or couldn’t move their muscles at all.
Participants were asked to perform speech attempts or think about simple words. Then, in another test, the participants heard or silently read the same words. The team could then map phonemes—the building blocks of speech—and run them through an AI decoder to reconstitute the inner thoughts of the participants. Willett and his team found that the resulting patterns were similar to (though less robust than) those of attempted speech signals from the 2023 study. They also developed unique in-system code phrases—phrases not common in usual speech (i.e. “Orange you glad I didn’t say banana”) that could switch the BCI on and off so that participants’ inner monologues remained private at their own discretion.
“We found that we could decode these signals well enough to demonstrate a proof of principle, although still not as well as we could with attempted speech,” Willett said in a press statement. “This gives us hope that future systems could restore fluent, rapid and comfortable speech to people with paralysis via inner speech alone.”
The system still has a ways to go before becoming a full-fledged mind reader. With just a 50-word vocabulary, the BCI produced an error rate up to 33 percent.
“It’s worth pointing out that implanted BCIs are not yet a widely available technology and are still in the earliest phases of research and testing,” Willett said in a press statement. “Improved hardware will enable more neurons to be recorded and will be fully implantable and wireless, increasing BCIs’ accuracy, reliability and ease of use.”
Willett also said that future studies will explore how to make the decoding process even more accurate, specifically by exploring regions of the brain beyond just the motor cortex, including those associated with language and hearing. With better science, engineering, and a little luck, science may one day be able to return voices to those who—through accidents or neurodegenerative diseases—have forever lost their own.
You Might Also Like
The Do’s and Don’ts of Using Painter’s Tape
The Best Portable BBQ Grills for Cooking Anywhere
Can a Smart Watch Prolong Your Life?
