Decoding intended speech with an intracortical brain-computer interface in a person with longstanding anarthria and locked-in syndrome

Intracortical brain-computer interfaces (iBCIs) for decoding intended speech have provided individuals with ALS and severe dysarthria an intuitive method for high-throughput communication. These advances have been demonstrated in individuals who are still able to vocalize and move speech articulators. Here, we decoded intended speech from an individual with longstanding anarthria, locked-in syndrome, and ventilator dependence due to advanced symptoms of ALS. We found that phonemes, words, and higher-order language units could be decoded well above chance. While sentence decoding accuracy was below that of demonstrations in participants with dysarthria, we can attain an extensive characterization of the neural signals underlying speech in a person with locked-in syndrome and, through our results, identify several directions for future improvement. These include closed-loop speech imagery training and decoding linguistic (rather than phonemic) units from neural signals in the middle prece..., , # Data from: Decoding intended speech with an intracortical brain-computer interface in a person with longstanding anarthria and locked-in syndrome

Dataset DOI: [10.5061/dryad.vq83bk481](https://doi.org/10.5061/dryad.vq83bk481)

## Description of the data and file structure

#### **Anarthric Speech iBCI Dataset**

**Overview**

These data are reported in Jude et al. 2026 and consist of separate sessions (listed below in “Session Table”) across a BrainGate2 clinical trial participant with anarthria and locked-in syndrome.

All data files are .mat files that can be loaded with MATLAB or Python (using the scipy function scipy.io.loadmat). Each .mat file is a single session block.

Alongside each .mat file, a .png image shows normalized neural features (threshold crossings and spike power) from a single trial in each .mat file block.

Accompanying code is available at [https://github.com/justin-jude/anarthria-speech-bci](https://github.com/justin-jude/anarthria-speech-bci).

Trial-by-trial..., No personally identifiable information (PII) is contained within this data. Only neural features and spoken sentences are present. No sentences spoken reveal personal information. Informed consent for data sharing was obtained.,