Thought-deciphering via hierarchical EEG-to-text alignment
Xiaopeng Mao, Morten Mørup, Xin Xu, Sang Wan Lee, Sadasivan Puthusserypady
原文摘要
Non-invasive brain-to-text interfaces offer alternative communication pathways for people with communication disabilities. However, sentence-level decoding from electroencephalography (EEG) remains challenging. We propose a hierarchical EEG-text alignment framework that retrieves previously unseen sentences by progressively decoding coarse-grained semantic information and fine-grained sentence representations. We hypothesize that broader semantic context can be more reliably captured from EEG than individual sentences. Accordingly, EEG representations are first classified into semantic classes, which are defined as groups of related sentences, followed by sentence retrieval within the predicted class. Among over 2,000 unique text samples, our approach achieves, on unseen sentences, average top-5 and top-10 retrieval accuracies of 62.6\% $\pm$ 1.0\% and 83.5\% $\pm$ 1.0\%, respectively, compared with 0.3\% $\pm$ 0.3\% and 0.5\% $\pm$ 0.2\% for direct EEG-sentence alignment without semantic classification. Qualitative analysis further reveals that decoding performance depends strongly on textual context. These findings demonstrate the potential of hierarchical semantic alignment for advancing sentence-level EEG-to-text decoding.
cs.LG · eess.SP