Gregory B. Cogan

This paper identifies distinct neural mechanisms for speech planning and execution using intracranial recordings.

This paper shows that speech BCIs can be trained on combined patient data by aligning neural data to a shared latent space, improving decoding performance compared to patient-specific models.

This study improves speech decoding accuracy using high-resolution ECoG recordings, achieving better phoneme decoding than standard methods.

This study shows that temporal fine structure (TFS) provides critical cues for speech segmentation, complementing the speech envelope (SE) in temporal information extraction.