Transformer-based neural speech decoding from surface and depth electrode signals

• Published in: Journal of neural engineering Vol. 22; no. 1; pp. 16017 - 16030
• Main Authors: Chen, Junbo, Chen, Xupeng, Wang, Ran, Le, Chenqian, Khalilian-Gourtani, Amirhossein, Jensen, Erika, Dugan, Patricia, Doyle, Werner, Devinsky, Orrin, Friedman, Daniel, Flinker, Adeen, Wang, Yao
• Format: Journal Article
• Language: English
• Published: England IOP Publishing 28.01.2025
• Subjects: Adult; Brain-Computer Interfaces; Deep Learning; ECoG; electrocorticographic; Electrocorticography - instrumentation; Electrocorticography - methods; Electrodes, Implanted; Electroencephalography - methods; Female; Humans; Male; neural speech decoding; neural speech prosthesis; Speech - physiology; speech synthesis; speech synthesis; neural speech prosthesis; neural speech decoding; ECoG; electrocorticographic

Objective. This study investigates speech decoding from neural signals captured by intracranial electrodes. Most prior works can only work with electrodes on a 2D grid (i.e. Electrocorticographic (ECoG) or ECoG array) and data from a single patient. We aim to design a deep-learning model architectur...