Speech mode classification from electrocorticography: transfer between electrodes and participants
- 31 July 2025
- journal article
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 22 (4) , 046033
Abstract
Objective. Speech brain–computer interfaces (BCIs) aim to restore communication for individuals who have lost the ability to speak by interpreting their brain activity and decoding the intended speech. As an initial component of these decoders, speech detectors have been developed to distinguish between the intent to speak and silence. However, it is important that these detectors account for real-life scenarios in which users may engage language-related brain areas—such as during reading or listening—without any intention to speak. Approach. In this study, we analyze the interplay between different speech modes: speaking, listening, imagining speaking, reading and mouthing. We gathered a large dataset of 29 participants implanted with electrocorticography electrodes and developed a speech mode classifier. We also assessed how well classifiers trained on data from a specific participant transfer to other participants, both in the case of a single- and multi-electrode classifier. Main results. High accuracy was achieved using linear classifiers, for both single-electrode and multi-electrode configurations. Single-electrode classification reached 88.89% accuracy and multi-electrode classification 96.49% accuracy in distinguishing among three classes (speaking, listening, and silence). The best performing electrodes were located on the superior temporal gyrus and sensorimotor cortex. We found that single-electrode classifiers could be transferred across recording sites. For multi-electrode classifiers, we observed that transfer performance was higher for binary classifiers compared to multiclass classifiers, with the optimal source subject of the binary classifiers depending on the speech modes being classified. Significance Accurately detecting speech from brain signals is essential to prevent spurious outputs from a speech BCI and to advance its use beyond lab settings. To achieve this objective, the transfer between participants is particularly valuable as it can reduce training time, especially in cases where subject training is challenging.Keywords
Funding Information
- Fonds Wetenschappelijk Onderzoek (FWO 11K2324N)
- Hercules Foundation (AKUL 043)
- KU Leuven (C24/18/098)
- Horizon 2020 Research and Innovation Programme (857375)
- HORIZON EUROPE Marie Sklodowska-Curie Actions (101118964)
This publication has 39 references indexed in Scilit:
- The nested hierarchy of overt, mouthed, and imagined speech activity evident in intracranial recordingsNeuroImage, 2023
- Imagined speech can be decoded from low- and cross-frequency intracranial EEG featuresNature Communications, 2022
- Neural oscillations track natural but not artificial fast speech: Novel insights from speech-brain coupling using MEGNeuroImage, 2021
- The temporal pole: From anatomy to function—A literature appraisalJournal of Chemical Neuroanatomy, 2021
- Automated anatomical labelling atlas 3NeuroImage, 2020
- Real-time decoding of question-and-answer speech dialogue using human cortical activityNature Communications, 2019
- Encoding of Articulatory Kinematic Trajectories in Human Speech Sensorimotor CortexNeuron, 2018
- On the interpretation of weight vectors of linear models in multivariate neuroimagingNeuroImage, 2014
- Functional organization of human sensorimotor cortex for speech articulationNature, 2013
- FreeSurferNeuroImage, 2012