Skip to main content
World Today News
  • Home
  • News
  • World
  • Sport
  • Entertainment
  • Business
  • Health
  • Technology
Menu
  • Home
  • News
  • World
  • Sport
  • Entertainment
  • Business
  • Health
  • Technology
Doctors analyzing a brain x-ray

Three BCI Advances Presented at Neuroscience 2026: Smartphone System, Locked-In Use, Singing Decoded

November 20, 2026 Health Desk Health

Brain-computer interfaces that restore speech to people paralyzed by ALS and brain injury took three leaps forward this week: one running on an iPhone, one working for a completely locked-in patient, and one that let a former singer produce a vocal scale with 84 percent accuracy.

Researchers presented all three at Neuroscience 2026, the Society for Neuroscience annual meeting in Washington, DC.

Key Clinical Takeaways:

  • A smartphone-based brain-to-text system decoded brain activity faster and with less memory than computer-based systems, using data from two BrainGate 2 trial participants.
  • A man with ALS in a completely locked-in state communicated through an implanted BCI for more than a year, even after losing eye movement — and his EEG readings looked like sleep while he was awake, raising concerns about misdiagnosed consciousness.
  • A brain-to-voice system at UC Davis produced speech that 94 percent of listeners understood, and decoded sung musical notes at 84 percent accuracy in a trained singer with ALS.

The clinical problem these devices attack is stark. People with amyotrophic lateral sclerosis, brain trauma, or stroke can lose the ability to speak or move voluntarily while their minds remain intact. Implantable BCIs record neural signals and translate them into text, synthesized speech, or device commands.

The technology remains experimental, available only inside clinical trials — but the researchers presenting this week said the path to broader use is shortening. “The hope is that in a few short years, these devices are going to become part of clinical care for people,” said Daniel Rubin, a neurologist at Mass General Brigham and Harvard Medical School, The Scientist reported.

Decoding Speech on a Phone, Not a Desktop

Most implanted BCI systems today depend on bulky computers with heavy processing and memory demands, and the delay between thought and output breaks the rhythm of conversation.

“These slow and variable response times can impede natural communication,” Chethan Pandarinath, a neuroscientist at the Georgia Institute of Technology and Emory University, said at the press conference, according to The Scientist. He said that the hardware requirement keeps patients tied to fixed systems rather than portable, always-available ones.

Pandarinath’s team took a different route: they adapted the dictation software already built into most smartphones. An adaptor converts brain signals into speech-like signals the phone’s dictation engine can recognize. Trained on recorded brain activity from two participants in the BrainGate 2 trial (NCT00912041), the smartphone system generated responses faster and required less memory than current computer-based setups.

Three BCI Advances Presented at Neuroscience 2026: Smartphone System, Locked-In Use, Singing Decoded
Photo: Yahoo

The system is now being tested in real time with trial participants. One participant described why it matters to her: when she wants to order food at a restaurant, people try to read her lips, which is difficult. She was excited that the technology could give her another option, The Scientist reported.

A Lifeline When Every Muscle Fails

Some paralyzed patients retain partial control — a lip movement, an eye flick — that eye-tracking technology can exploit. In locked-in syndrome, the extreme end of paralysis, even that is gone.

Rubin’s team worked with one such patient with ALS who still had eye movement when they implanted a BCI decoding imagined movements of different body parts, letting him spell and select words. Over a year, he lost eye movement too, leaving the implant as his only channel to the outside world.

“We quickly set out to make sure that he could use this system anytime he needed, and importantly, that he could use this system when our team wasn’t present,” Rubin said, The Scientist reported. His team trained the patient’s caregivers to set up and calibrate the device.

A calibration problem surfaced: the system could not be calibrated while the patient slept, and in his locked-in state his team struggled to tell when he was awake. When they turned to electroencephalogram signals — the standard method for distinguishing sleep from wakefulness — the readings defied expectation. His EEG not only differed from people without locked-in syndrome but registered as sleep-like stages while he was awake and communicating through the BCI.

“What this told us was that there may be many other people who are like him who are believed to be unconscious based on measurements performed using EEG who may in fact be awake and in a locked-in state and unable to communicate due to paralysis,” Rubin said.

If EEG misclassifies locked-in consciousness as sleep, some patients now treated as unresponsive may be reachable with the right interface.

Restoring the Voice, Not Just the Words

Maitreyee Wairagkar, a neuroscientist at the University of California, Davis, presented a brain-to-voice system that skips text entirely. Probes implanted in the speech motor cortex — the region controlling lips, jaw, and tongue — feed electrical activity to an AI decoder that converts it directly into audible words played through a speaker. The pipeline runs fast enough for natural conversation, The Scientist reported.

When listeners heard recordings of the reconstructed speech, 94 percent understood it. TechTimes noted a caveat: that intelligibility figure came from reanalyzed previously collected neural data, and it remains unproven whether the system performs at the same level during live, real-time conversation.

Wairagkar pushed the work further, into expression. “Our speech is more than just words,” she said, The Scientist reported. Pauses, intonation, and pitch carry meaning; “we emote through our voice.” Her team tested pitch decoding with a 58-year-old woman with ALS who had been a trained singer before losing her speech.

The system decoded the notes she sang from a musical scale with 84 percent accuracy. Yahoo, citing reporting published Nov. 14 in The New York Times, added a human detail the conference slides could not: the woman reportedly cried tears of joy afterward. The singing findings remain preliminary.

The UC Davis work builds on an established track record. Casey Harrell, a man with ALS, received four implanted arrays containing 256 electrodes in 2023. UC Davis Health reported in June that he had used a related brain-to-text interface at home for more than 3,800 hours and produced nearly 2 million words over almost two years — communicating, working, and using digital tools without researchers present.

How Close Is Clinical Use?

Nothing presented this week changes the standard of care. Implanted BCIs require brain surgery, remain confined to clinical trials, and TechTimes was blunt about the limits: there is no cure for ALS, and the technology will not restore a person’s original voice. The commercial pull is visible, though — Medical Xpress cited projections that the global BCI market will grow from $1.7 billion in 2022 to $6.2 billion by 2030.

Cynthia Chestek, a biomedical engineer at the University of Michigan who moderated the session, framed the stakes. “The ability to decode and convert brain activity into spoken or written words has life-changing potential for people with paralysis,” she said. “The work presented today brings brain-to-voice and brain-to-text technologies closer to reaching people outside of clinical trials, which is extremely exciting.”

For patients and families weighing clinical trial participation, the practical step is identifying active BCI trials — the BrainGate 2 study is registered on ClinicalTrials.gov — and discussing eligibility with a neurologist familiar with neuromodulation research centers.

Leigh Hochberg, a neuro-intensive care physician at Mass General Brigham who led the press conference, called the devices “some of the most exciting examples of the translation of fundamental neuroscience and neuroengineering toward clinical care,” The Scientist reported.

What remains unanswered is the question TechTimes put plainly: whether 94 percent intelligibility holds up in live conversation, and whether the systems perform across people with varying degrees of speech impairment. Until researchers show that in real time, the distance between laboratory demonstration and a device a patient can take home stays unmeasured.

The Washington, DC gathering fits the host organization. The Society for Neuroscience was founded in 1969 by Ralph W. Gerard and has grown into the largest neuroscience society in the world, with nearly 35,000 members.

Its first annual meeting, held in Washington in October 1971, drew just 1,396 scientists; the 2024 meeting in Chicago drew 22,359 attendees.

That scale of growth came in part from meeting formats like this week’s press conference, part of the society’s stated mission to promote public information about neuroscience and to inform legislators and other policy makers about the implications of research for public policy and continued scientific progress. The society also publishes The Journal of Neuroscience, launched in 1981, and the open-access journal eNeuro, launched in 2014.

Disclaimer: The information provided in this article is for educational and scientific communication purposes only and does not constitute medical advice. Always consult with a qualified healthcare provider regarding any medical condition, diagnosis, or treatment plan.

Share this:

  • Share on Facebook (Opens in new window) Facebook
  • Share on X (Opens in new window) X

Related reading

  • UCSF Study: Wernicke’s Area Also Launches Speech Production
  • Gut Bacterium Sugar May Help Burn Visceral Fat and Combat Obesity
  • RBA's Fifth Hike Adds About A$94 a Month on A$600,000; Three Voted to Hold (daybreakwire.com)

Related

Search:

World Today News

World Today News is your trusted source for global journalism — breaking headlines, in-depth analysis, and reporting from around the world.

Quick Links

  • Privacy Policy
  • About Us
  • Accessibility statement
  • California Privacy Notice (CCPA/CPRA)
  • Contact
  • Cookie Policy
  • Disclaimer
  • DMCA Policy
  • Do not sell my info
  • EDITORIAL TEAM
  • Terms & Conditions

Browse by Location

  • GB
  • NZ
  • US

Connect With Us

© 2026 World Today News. All rights reserved. Your trusted global news source directory.
For contact, advertising, copyright, issues email: [email protected]

Privacy Policy Terms of Service