Giving Voice to the Voiceless

This piece, by Selina Hui, was published on 04/01/25. Image credits: Liam Drew, 2022

Brain-computer interfaces (BCIs) are promising technologies that analyze brain signals from thoughts and translate them into actions through output devices. The goal is to restore lost function to individuals with neurodegenerative disorders. Neurological conditions that may cause speech impairment include stroke, Parkinson’s Disease, and Amyotrophic Lateral Sclerosis (ALS). These conditions can affect speech production and language processing, leading to disorders like aphasia (difficulty understanding or producing speech).

The first significant breakthrough in speech restoration occurred in 2009 when Dr. Philip Kennedy and his colleagues at Neural Signals, Inc., in collaboration with the Guenther Lab, developed the world’s first BCI capable of translating neural signals into synthetic speech output in real-time. This groundbreaking device decoded neural signals from an electrode implanted in the speech motor cortex of a patient with locked-in syndrome (paralysis of voluntary muscles), allowing him to produce vowel sounds by imagining speech.

In the past five years, AI and machine learning advances have revolutionized speech BCIs, improving their ability to analyze neural data and leading to significant breakthroughs.

In a study published in the New England Journal of Medicine in August 2024, researchers from UC Davis Health successfully created one of the most accurate speech neuroprosthesis BCIs ever reported. The study showed a system capable of translating brain signals into speech with up to 97% accuracy. This BCI allowed a 45-year-old man with ALS and severely impaired speech to communicate his intended sentences through speech on a computer within minutes of activation. Amazingly, the decoded words were read aloud in his pre-ALS, created using text-to-speech software trained with audio samples. Neuroscientist Sergey Stavisky reported that the patient "cried with joy" as his intended words appeared correctly on the screen.

These advancements are a game-changer for restoring communication in ALS patients, who progressively lose motor control and speech. This technology allows them to engage in meaningful conversations with friends, family, and caregivers, potentially restoring their sense of connection. Dr. David Brandman, one of the lead researchers, emphasized the transformative nature of this technology, stating that it "provides hope for people who want to speak but can’t". This hope extends beyond speech restoration, giving people back their voice and ability to participate in the world around them fully.

While invasive speech BCIs have shown remarkable progress in restoring communication for individuals with severe paralysis, the inherent risks associated with brain implants continue to be a concern. These risks include infection, inflammation, tissue damage, and potential complications from brain surgery. To make BCIs more accessible, researchers should focus on developing systems that don't require surgery. Researchers should improve how we interpret brain signals by combining various methods of reading brain activity to create more user-friendly devices.

In the future, a worthy area of research is developing noninvasive alternatives that can achieve similar results without surgery or brain implantation. These advancements can increase the accessibility of speech restoration, potentially helping not just those with severe paralysis but also people with milder speech difficulties or other neurological conditions. As this technology continues to evolve, the future of communication assistance shines with the promise of restoring voices and reconnecting lives in ways we once thought impossible.

Want to submit a piece? Or trying to write a piece and struggling? Check out the guides here!

Thank you for reading. Reminder: Byte Sized is open to everyone! Feel free to submit your piece. Please read the guides first though.

All submissions to berkan@usc.edu with the header “Byte Sized Submission” in Word Doc format please. Thank you!