Related Experiment Video
Updated: Jun 17, 2025
Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages
Published on: March 24, 2023
An Accurate and Rapidly Calibrating Speech Neuroprosthesis
Nicholas S Card1, Maitreyee Wairagkar1, Carrina Iacobacci1
1From the Departments of Neurological Surgery (N.S.C., M.W., C.I., X.H., T.S.-C., M.V.N., A.S., K.S., S.D.S., D.M.B.), Computer Science (X.H., M.V.N.), and Biomedical Engineering (T.S.-C., A.S.), University of California, Davis, Davis, and the Departments of Neurosurgery (D.R.D., E.Y.C., J.M.H.), Electrical Engineering (E.M.K.), and Computer Science (C.F.), the Wu Tsai Neurosciences Institute (E.M.K., J.M.H.), the Howard Hughes Medical Institute (F.R.W.), and Bio-X (J.M.H.), Stanford University, Stanford - both in California; the Departments of Radiology and Neuroscience, Washington University School of Medicine, Saint Louis (M.F.G.); the School of Engineering and Carney Institute for Brain Sciences, Brown University (L.R.H.), and the Center for Neurorestoration and Neurotechnology, Department of Veterans Affairs Office of Rehabilitation Research and Development, VA Providence Healthcare (L.R.H.) - both in Providence, RI; and the Center for Neurotechnology and Neurorecovery, Department of Neurology, Massachusetts General Hospital, Harvard Medical School, Boston (L.R.H.).
A novel brain-computer interface decodes attempted speech into text, restoring communication for individuals with paralysis. This speech neuroprosthesis achieved high accuracy and enabled conversational abilities after minimal training.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Assistive Technology
Background:
- Brain-computer interfaces (BCIs) offer communication pathways for individuals with paralysis by translating brain activity into text.
- Current BCIs face limitations due to extensive training needs and suboptimal accuracy, hindering widespread adoption.
Purpose of the Study:
- To evaluate the efficacy of an intracortical speech neuroprosthesis in restoring conversational communication for a patient with amyotrophic lateral sclerosis (ALS).
- To assess the accuracy and speed of speech decoding using a BCI system in a real-world conversational setting.
Main Methods:
- Surgical implantation of microelectrode arrays into the left ventral precentral gyrus of a 45-year-old male participant with ALS and severe dysarthria.
- Recording of 256 intracortical electrodes to capture neural activity during attempted speech.
- Decoding of cortical neural activity to generate text, which was then vocalized using text-to-speech software.
Main Results:
- High accuracy (99.6%) with a 50-word vocabulary was achieved on the first day of use (25 days post-surgery) after 30 minutes of calibration.
- After 1.4 hours of additional training, the system achieved 90.2% accuracy with a 125,000-word vocabulary.
- Sustained accuracy of 97.5% over 8.4 months, enabling conversational communication at approximately 32 words per minute for over 248 hours.
Conclusions:
- An intracortical speech neuroprosthesis can effectively restore conversational communication in individuals with ALS and severe dysarthria.
- The system demonstrated high accuracy and usability after a brief training period, significantly improving the participant's communication abilities.
