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

Timothée Proix (1) , Jaime Delgado Saa (1) , Andy Christen (1) , Stephanie Martin (1) , Brian N Pasley (2) , Robert T Knight (2) , Xing Tian (3, 4) , David Poeppel (5, 6) , Werner K Doyle (7) , Orrin Devinsky (7) , Luc H Arnal (8) , Pierre Mégevand (1) , Anne-Lise Giraud (1)

1 Department of Basic Neurosciences
2 UC Berkeley - University of California [Berkeley]
3 New York University [Shanghai]
4 ECNU - East China Normal University [Shangaï]
5 Ernst Strüngmann Institute for Neuroscience
6 NYU - New York University [New York]
7 NYU Grossman School of Medicine - New York University School of Medicine
8 IDA - Institut de l'Audition [Paris]

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.

Domaines: Neurosciences

Timothée Proix, Jaime Delgado Saa, Andy Christen, Stephanie Martin, Brian N Pasley, et al.. Imagined speech can be decoded from low- and cross-frequency intracranial EEG features. Nature Communications, 2022, 13 (1), pp.48. ⟨10.1038/s41467-021-27725-3⟩. ⟨hal-03993899⟩