When Ann Johnson experienced a brainstem stroke at 30, her life changed drastically. While playing volleyball with friends, she lost control of her muscles, rendering her unable to move or speak—a condition known as locked-in syndrome. Eighteen years later, thanks to developments at UC Berkeley and UC San Francisco, Ann has begun to regain her ability to communicate.
The breakthrough comes from a brain-computer interface designed to restore speech functions for those affected by severe paralysis or similar conditions. This research holds promise for increasing accessibility in the workforce and wider world for individuals with disabilities. In 2022, Ann participated in a clinical trial as the third subject, helping to test an AI model developed by UC Berkeley researchers, including Assistant Professor Gopala Anumanchipalli and Ph.D. student Kaylo Littlejohn.
Gopala Anumanchipalli, who collaborates with neurosurgeon Edward Chang from UC San Francisco, explained, “As part of the postdoc, we were able to get a good sense of, like, here is the part of the brain that is actually responsible for speech production, and here is how we can computationally model this process so we can synthesize just from brain activity what someone might be saying.” This technology bypasses the damaged connection between the brain and body, utilizing a neuroprosthesis to communicate speech signals from the brain to an external device.
The system trains on specific neural patterns when Ann attempts to speak, allowing the AI to translate these into speech or text. Kaylo Littlejohn noted, “Training the decoders and also working with the participant, working with clinical research coordinators to really try and train a good model that can translate Ann’s brain activity into the desired output, which is to restore her natural voice and the content of what she’s trying to say.”
Although the process involves some delay and requires significant computer integration, recent advancements have reduced the response time significantly, offering real-time speech synthesis. Anumanchipalli believes that the evolution of photorealistic avatars and wireless technology could soon lead to improved outcomes: “I definitely think so. But, you know, that’s the thing, we need multiple avenues with which developments must happen.”
Ann’s story highlights the potential of combining neuroscience, AI, and technology to improve life quality for those facing similar challenges. Anumanchipalli noted, “We didn’t want to read her mind. We really wanted to give her the agency to do this.” Moving forward, researchers aim to streamline the technology for broader clinical use, bringing about a new standard of care.
In the near future, the hope is that individuals like Ann will have the tools they need to communicate seamlessly with others, revolutionizing how disabilities impact daily life.
