Imagined speech can be decoded from low- and cross-frequency intracranial EEG features

• Published in: Nature communications Vol. 13; no. 1; p. 48
• Main Authors: Proix, Timothée, Delgado Saa, Jaime, Christen, Andy, Martin, Stephanie, Pasley, Brian N, Knight, Robert T, Tian, Xing, Poeppel, David, Doyle, Werner K, Devinsky, Orrin, Arnal, Luc H, Mégevand, Pierre, Giraud, Anne-Lise
• Format: Journal Article
• Language: English
• Published: England Nature Publishing Group 10.01.2022; Nature Publishing Group UK; Nature Portfolio
• Subjects: Adult; Algorithms; Articulatory phonetics; Brain; Brain - diagnostic imaging; Brain Mapping; Brain-Computer Interfaces; Cognitive science; Decoding; EEG; Electrocorticography; Electrodes; Epilepsy; Feature extraction; Female; Human-computer interface; Humans; Imagination; Information processing; Interfaces; Language; Learning algorithms; Machine learning; Male; Middle Aged; Neuroscience; Patients; Phonetics; Speech; Speech perception; Speech production; Speech recognition; Young Adult
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-021-27725-3

Reconstructing intended speech from neural activity using brain-computer interfaces holds great promises for people with severe speech production deficits. While decoding overt speech has progressed, decoding imagined speech has met limited success, mainly because the associated neural signals are weak and variable compared to overt speech, hence difficult to decode by learning algorithms. We obtained three electrocorticography datasets from 13 patients, with electrodes implanted for epilepsy evaluation, who performed overt and imagined speech production tasks. Based on recent theories of speech neural processing, we extracted consistent and specific neural features usable for future brain computer interfaces, and assessed their performance to discriminate speech items in articulatory, phonetic, and vocalic representation spaces. While high-frequency activity provided the best signal for overt speech, both low- and higher-frequency power and local cross-frequency contributed to imagined speech decoding, in particular in phonetic and vocalic, i.e. perceptual, spaces. These findings show that low-frequency power and cross-frequency dynamics contain key information for imagined speech decoding.