Reproduce “Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zihan Zhang, Yu Bao, Xiao Ding, Tianyi Jiang, Kai Xiong
The paper introduces COFETT, an EEG-to-text benchmark that repeats imagined sentences across sessions to address changing EEG patterns. It trains EEG representations toward pretrained sentence embeddings and evaluates Pearson correlation with text representations, without supplying the correct previous word. For EEGPT, correlation was 17.13% with EEG versus 6.51% with noise. This shows alignment, not free-running text generation, in two participants.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.