Zachary V. Freudenburg

This study shows that a small, optimally placed ECoG grid can achieve high word classification accuracy for speech BCIs, reducing surgical risks and device complexity.

This paper reconstructs articulatory features from brain signals using generalizable features from able-bodied individuals, achieving high correlation in three participants.

This paper optimizes deep learning models for speech reconstruction from sensorimotor brain activity, achieving high word decoding accuracy and intelligible speech.

The paper introduces a multimodal dataset combining iEEG and fMRI data from naturalistic audiovisual stimulation to study neural mechanisms across recording modalities.