/ EN
2026-09-10 00:00 China Papers Foundations & Methods Translated from EN

OPM-MEG Beats EEG by 3.6 Points in Non-Invasive Speech Decoding

Summary Ten native Mandarin speakers read aloud six single-vowel rhymes while optically pumped magnetometer magnetoencephalography (OPM-MEG) and EEG recorded the same task. In the 150-500 ms window after stimulus onset, OPM-MEG decoded significantly more accurately than EEG with all five classifiers tested. The best-performing combination, common spatial pattern features with a linear support vector machine, reached a mean accuracy of 60.3% for OPM-MEG versus 56.7% for EEG. That suggests speech BCIs that need no implanted electrodes and do not restrict head movement may have a clearer signal path than EEG.
Why it matters Speech BCIs have long been held back by blurry non-invasive signals. This study compares two non-invasive methods head-to-head on the same task, the same participants and the same analysis pipeline rather than in separate experiments, which is what makes the result comparable. The margin is small, 3.6 percentage points, but it points the same way throughout, and OPM-MEG tolerates head movement, which is exactly what speech tasks require.

BCIwiki (bciwiki.com) — Optically pumped magnetometer magnetoencephalography (OPM-MEG) decoded speech production more accurately than EEG in the same task and the same participants, a team from the Department of Neurosurgery at Huashan Hospital, Fudan University and Beihang University’s School of Instrumentation Science and Opto-electronics Engineering reported. Within the 150-500 ms window after stimulus onset, all five classifiers showed significant OPM-MEG over EEG clusters. The study appeared in NeuroImage on September 10, 2026.

Ten native Mandarin speakers produced six isolated vowel rhymes, 100 repetitions per class, while OPM-MEG and EEG were recorded under the same task. The team compared six feature representations and five classifiers using time-resolved decoding, temporal generalization, pairwise classification and source-space searchlight analyses. Decoding stayed near chance before stimulus onset and rose afterward.

Averaged across classifiers over 150-500 ms, common spatial patterns (CSP) was the strongest feature representation, at 57.9% for OPM-MEG and 55.0% for EEG. Across features, a linear support vector machine (Linear SVM) reached the highest mean accuracy, 56.4% and 54.1% respectively. CSP with Linear SVM was the best combination, yielding mean accuracies of 60.3% for OPM-MEG and 56.7% for EEG, with late peak accuracies of 63.0% and 60.1%. In the pairwise analysis, CSP with Linear SVM averaged 60.1%, and the vowel contrast /i/ versus /u/ peaked at 61.2%.

Temporal-generalization matrices were dominated by a narrow main diagonal, with limited off-diagonal generalization between 50.7% and 52.1%, indicating predominantly time-specific discriminative information. Exploratory source-space searchlight analysis identified cortical parcels with above-chance local decoding from 100 to 450 ms, while no parcel reached significance at 0 or 50 ms. The authors note these patterns do not directly establish activation or coherent functional-network recruitment.

The authors present the results as support for OPM-MEG as a high-resolution non-invasive platform for time-resolved decoding, and as practical guidance for feature and classifier selection in speech-related neuroimaging and brain-computer interface studies. All accuracies come from 10 participants and six vowel-rhyme classes, and have not been validated on continuous sentences or larger vocabularies.

Compiled by BCIwiki from public sources

Sources · 1

Huashan Hospital timeline

2026-07 NeuroXess Registers Fully Implanted Wireless Functional BCI Study for Upper-Limb Functional Replacement 2026-05 sEEG Study Finds Motor Imagery Activity Shifts by Task Stage and Frequency Band 2026-05 Huashan Hospital Completes BCI Trial Comparing 3 Motor Imagery Modes in 54 Stroke Patients 2025-01 NeuroXess Decodes 142 Mandarin Syllables at 71% Accuracy All entries →
Read original ↗
Suggest a correction Revisions · none / EN
© 2026 BCIwiki.com Digest Topics Tips Subscribe Revisions About