CCSUMSP: A cross-subject Chinese speech decoding framework with unified topology and multi-modal semantic pre-training

Shuai Huang, Yongxiong Wang, Huan Luo

Abstract: Highlights•Develop a unified topological representation(UTR) for better cross-subject EEG generalization.•Design a multi-modal pre-training strategy combining EEG and eye-tracking data.•Introduce a dynamic multi-view decoder(DMD) for adaptive brain region weighting.