Cross-subject decoding of imagined speech from scalp EEG: a leakage-controlled evaluation on three public corpora
Abstract
Objective. A decoder of imagined speech that works for a new user without calibration would make a non-invasive speech interface practical. We tested whether imagined-speech content recorded with scalp electroencephalography (EEG) transfers across people, and examined why accuracy within a single person remains low. Approach. We analyzed three public corpora, ds003626, KaraOne and Track 3 of the 2020 International Brain-Computer Interface Competition, under a protocol that enforces split integrity by assertion and reports exact binomial thresholds, group tests and bootstrap confidence intervals. We trained decoders on each participant and tested them on every other, compared representational geometry across participants without a classifier, applied subject-level alignment, and tested five explanations for the within-subject ceiling. Main results. Across 482 ordered pairs of participants, no pair survived correction for multiple comparisons; mean pair-transfer accuracy lay within 0.006 of chance on every corpus, while every within-subject reference lay above it. Imagery against pre-stimulus rest generalized at about 0.61 after artifact and elapsed-time controls, but its decoder labelled the interval preceding imagery as imagery as often as imagery itself, so the contrast reflects a post-stimulus state, not imagery. Within subject, only the competition corpus decoded above threshold for every participant (0.3147; chance 0.200); syllable count explained little of this, but its frequency profile failed an artifact audit. Significance. In these corpora, imagined-speech content did not transfer between people through any representation we examined. Trial count per class was the only variable that ordered the corpora, which favors larger single-condition datasets over further model development.
Related
- Leakage-Audited Benchmarking Reveals Limited Evidence for Cross-Subject Auditory-Evoked EEG Vowel Perception Decoding
- Window leakage in clinical EEG machine learning: matched subject-independent evaluation across ADHD and Parkinson cohorts
- Semantic Alignment of EEG and Text: A Contrastive Learning Framework for Decoding Imagined Speech
- Reproducibility and Leakage-Controlled Evaluation of Machine-Learning Models for Chronic Kidney Disease Classification
- Subject-independent classification of ADHD from pediatric EEG: a leakage-aware deep learning framework with interpretable neurophysiological mapping
BibTeX
@misc{adeika2026crosssubject,
title = {{Cross-subject decoding of imagined speech from scalp EEG: a leakage-controlled evaluation on three public corpora}},
author = {Blessing Isoyiza Adeika and Onyema Osuagwu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.20954},
eprint = {2610.20954},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.20954},
}
RIS
TY - UNPB
TI - Cross-subject decoding of imagined speech from scalp EEG: a leakage-controlled evaluation on three public corpora
AU - Blessing Isoyiza Adeika
AU - Onyema Osuagwu
PY - 2026
DA - 2026/10/14
PB - arXiv
DO - 10.48550/arxiv.2610.20954
UR - https://arxiv.org/abs/2610.20954
AB - Objective. A decoder of imagined speech that works for a new user without calibration would make a non-invasive speech interface practical. We tested whether imagined-speech content recorded with scalp electroencephalography (EEG) transfers across people, and examined why accuracy within a single person remains low. Approach. We analyzed three public corpora, ds003626, KaraOne and Track 3 of the 2020 International Brain-Computer Interface Competition, under a protocol that enforces split integrity by assertion and reports exact binomial thresholds, group tests and bootstrap confidence intervals. We trained decoders on each participant and tested them on every other, compared representational geometry across participants without a classifier, applied subject-level alignment, and tested five explanations for the within-subject ceiling. Main results. Across 482 ordered pairs of participants, no pair survived correction for multiple comparisons; mean pair-transfer accuracy lay within 0.006 of chance on every corpus, while every within-subject reference lay above it. Imagery against pre-stimulus rest generalized at about 0.61 after artifact and elapsed-time controls, but its decoder labelled the interval preceding imagery as imagery as often as imagery itself, so the contrast reflects a post-stimulus state, not imagery. Within subject, only the competition corpus decoded above threshold for every participant (0.3147; chance 0.200); syllable count explained little of this, but its frequency profile failed an artifact audit. Significance. In these corpora, imagined-speech content did not transfer between people through any representation we examined. Trial count per class was the only variable that ordered the corpora, which favors larger single-condition datasets over further model development.
ER -