SpellerSSL: Self-Supervised Learning with P300 Aggregation for Speller BCIs

Jiazhen Hong, Geoffrey Mackellar, Soheila Ghane

TL;DR: SpellerSSL combines self-supervised learning and P300 aggregation to achieve state-of-the-art ITR and reduce calibration by 60% in P300 spellers.

Abstract: Electroencephalogram (EEG)-based P300 speller brain–computer interfaces (BCIs) face three main challenges: low signal-to-noise ratio (SNR), poor generalization, and time-consuming calibration. We propose SpellerSSL, a framework that integrates self-supervised learning (SSL) with P300 aggregation to address these issues. First, we introduce an aggregation strategy to enhance SNR. Second, a customized 1D U-Net backbone is pretrained on cross- and in-domain EEG to improve generalization, and then fine-tuned with a lightweight ERP-Head classifier for subject-specific P300 detection. Our evaluations on calibration time demonstrate that combining the aggregation strategy with SSL significantly reduces the calibration burden per subject and improves robustness across subjects. Experimental results show that SSL learns effective EEG representations in both in-domain and cross-domain, with in-domain achieving a state-of-the-art character recognition rate of 94\% with only 7 repetitions and the highest information transfer rate (ITR) of 21.86~bits/min on the public II-B dataset. Moreover, in-domain SSL with P300 aggregation reduces the required calibration size by 60\% while maintaining a comparable character recognition rate. To our knowledge, this is the first study to apply SSL to P300 spellers, highlighting its potential to improve both efficiency and generalization in speller BCIs and paving the way toward an EEG foundation model. The code is available at: https://github.com/Emotiv/SpellerSSL-NeurIPS2025

Length: long paper (up to 8 pages)

Domain: methods

Author List Check: The author list is correctly ordered and I understand that additions and removals will not be allowed after the abstract submission deadline.

Anonymization Check: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and URLs that point to identifying information.

Submission Number: 16