Cross-subject generalization in EEG-based brain-computer interfaces (BCIs) remains challenging due to individual variability in neural signals. We investigate whether spectral representations offer more stable features for cross-subject transfer than temporal waveforms. Through correlation analyses across three EEG paradigms (SSVEP, P300, and Motor Imagery), we find that spectral features exhibit consistently higher cross-subject similarity than temporal signals. Motivated by this observation, we introduce ASPEN, a hybrid architecture that combines spectral and temporal feature streams via multiplicative fusion, requiring cross-modal agreement for features to propagate. Experiments across six benchmark datasets reveal that ASPEN is able to dynamically achieve the optimal spectral-temporal balance depending on the paradigm. ASPEN achieves the best unseen-subject accuracy on three of six datasets and competitive performance on others, demonstrating that multiplicative multimodal fusion enables effective cross-subject generalization.

翻译：基于脑电图（EEG）的脑机接口（BCI）中，由于神经信号的个体差异性，跨被试泛化仍具挑战性。本研究探讨了谱表征是否比时域波形能提供更稳定的跨被试迁移特征。通过对三种EEG范式（稳态视觉诱发电位、P300和运动想象）进行跨被试相关性分析，我们发现谱特征在跨被试间的一致性始终高于时域信号。基于这一观察，我们提出了ASPEN——一种通过乘法融合结合谱特征流与时域特征流的混合架构，该架构要求特征在跨模态间达成一致才能向前传播。在六个基准数据集上的实验表明，ASPEN能够根据不同范式动态实现最优的谱-时平衡。ASPEN在其中三个数据集上取得了最优的未见被试准确率，在其他数据集上也表现出具有竞争力的性能，这证明了乘法多模态融合能够实现有效的跨被试泛化。