Delineating neural contributions to electroencephalogram-based speech decoding
Journal of Neural Engineering · 01.10.2026 · 23 (5) · 056062
DOI: 10.1088/1741-2552/aeb68d ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Neural Engineering, online erschienen am 30.10.2026. Verfasst von Motoshige Sato und 11 weiteren Autor:innen. Beteiligte Einrichtung: Araya Inc., Tokyo, Japan. Hauptthemen laut MEDLINE: Electroencephalography, Brain-Computer Interfaces, Speech. Die Arbeit nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Moonshot Research and Development Program.
Abstract (Originalsprache)
Objective . Speech brain–computer interfaces (BCIs) have emerged as a pivotal technology in facilitating communication for individuals with speech impairments. Utilizing electroencephalography (EEG) for noninvasive speech BCIs offers an accessible and affordable solution, potentially benefiting a broader audience. However, EEG-based speech decoding remains controversial especially for overt speech, due to difficulties in separating speech-related neural activities from myoelectric potential artifacts generated during articulation. Moreover, because paradigms for collecting covert speech data are inherently less scalable than those for overt speech, whether the neural dynamics underlying EEG-based decoding of overt speech are also present during covert speech remains an open and practically important question. Approach . Here we aim to delineate the extent of the neural contributions to EEG-based speech decoding, and the degree to which the underlying neural dynamics are shared across overt and covert speech, by employing Explainable AI techniques to a convolutional neural network predicting spoken words based on signals obtained by ultra-high-density (uhd)-EEG. Main results . We found that electrode-wise contributions to the decoding cannot be explained by their mutual information with electromyography (EMG). Furthermore, contributing periods of speech to EEG-based decoding are distinct from those to decoding solely relying on EMG. Contributing periods of EEG-based decoding partially overlapped between overt and minimally overt speech. Notably, the denoising process successfully enhanced the decoding contribution from electrodes within speech-related brain areas for all speech conditions. Significance . Altogether, our findings support the idea that, with appropriate preprocessing, EEG becomes a valuable tool for decoding spoken words based on underlying neural activities.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Araya Inc., Tokyo, Japan.
- Sincxpress Education SRL, Bucharest, Romania.
ORCID-Profile: Motoshige Sato, Eri Hatakeyama, Masakazu Inoue, Sensho Nobe, Akito Yoshida, Atsushi Yamamoto, Kenichi Tomeoka, Michael X Cohen, Shuntaro Sasai
Förderung
- Moonshot Research and Development Program
Zitieren
APA
Sato, M., Hatakeyama, E., Inoue, M., Kabe, Y., Nobe, S., Yoshida, A., Yamamoto, A., Kita, Y., Shimizu, M., Tomeoka, K., Cohen, M. X., & Sasai, S. (2026). Delineating neural contributions to electroencephalogram-based speech decoding. Journal of Neural Engineering, 23(5), 056062. https://doi.org/10.1088/1741-2552/aeb68d
Vancouver
Sato M, Hatakeyama E, Inoue M, Kabe Y, Nobe S, Yoshida A, et al. Delineating neural contributions to electroencephalogram-based speech decoding. Journal of Neural Engineering. 2026;23(5):056062. doi:10.1088/1741-2552/aeb68d
BibTeX
@article{Sato2026,
author = {Sato, Motoshige and Hatakeyama, Eri and Inoue, Masakazu and Kabe, Yasuo and Nobe, Sensho and Yoshida, Akito and Yamamoto, Atsushi and Kita, Yuya and Shimizu, Mayumi and Tomeoka, Kenichi and Cohen, Michael X and Sasai, Shuntaro},
title = {Delineating neural contributions to electroencephalogram-based speech decoding},
journal = {Journal of Neural Engineering},
year = {2026},
volume = {23},
number = {5},
pages = {056062},
doi = {10.1088/1741-2552/aeb68d}
}
EUVIMED