An Accurate and Rapidly Calibrating Speech Neuroprosthesis

TLDR

Brain–computer interfaces can enable communication for people with paralysis by converting cortical activity associated with attempted speech into text, but their use has been limited by extensive training requirements and low accuracy. This study reports the decoding of cortical neural activity during both prompted and unstructured speech attempts in an ALS patient with severe dysarthria. The neuroprosthesis used four intracortical electrode arrays in the left ventral precentral gyrus, calibrated with 30 minutes of speech‑attempt recordings, decoded words, and rendered them via text‑to‑speech mimicking the patient’s pre‑ALS voice. After brief training, the system achieved 99.6 % accuracy with a 50‑word vocabulary on day one, 90.2 % with a 125,000‑word vocabulary after 1.4 h more training, and maintained 97.5 % accuracy over 8.4 months while enabling 32 wpm self‑paced communication for over 248 hours. The study was funded.

Abstract

BackgroundBrain–computer interfaces can enable communication for people with paralysis by transforming cortical activity associated with attempted speech into text on a computer screen. Communication with brain–computer interfaces has been restricted by extensive training requirements and limited accuracy.MethodsA 45-year-old man with amyotrophic lateral sclerosis (ALS) with tetraparesis and severe dysarthria underwent surgical implantation of four microelectrode arrays into his left ventral precentral gyrus 5 years after the onset of the illness; these arrays recorded neural activity from 256 intracortical electrodes. We report the results of decoding his cortical neural activity as he attempted to speak in both prompted and unstructured conversational contexts. Decoded words were displayed on a screen and then vocalized with the use of text-to-speech software designed to sound like his pre-ALS voice.ResultsOn the first day of use (25 days after surgery), the neuroprosthesis achieved 99.6% accuracy with a 50-word vocabulary. Calibration of the neuroprosthesis required 30 minutes of cortical recordings while the participant attempted to speak, followed by subsequent processing. On the second day, after 1.4 additional hours of system training, the neuroprosthesis achieved 90.2% accuracy using a 125,000-word vocabulary. With further training data, the neuroprosthesis sustained 97.5% accuracy over a period of 8.4 months after surgical implantation, and the participant used it to communicate in self-paced conversations at a rate of approximately 32 words per minute for more than 248 cumulative hours.ConclusionsIn a person with ALS and severe dysarthria, an intracortical speech neuroprosthesis reached a level of performance suitable to restore conversational communication after brief training. (Funded by the Office of the Assistant Secretary of Defense for Health Affairs and others; BrainGate2 ClinicalTrials.gov number, NCT00912041.)