Search papers, labs, and topics across Lattice.
This study critically evaluates the feasibility of EEG-to-text (EEG2Text) systems in real-world applications, highlighting the limitations of current benchmarks that rely on teacher-forcing evaluation. By addressing the issue of EEG instability and introducing the Corpus OF Eeg-To-Text (COFETT), the authors provide a robust framework for assessing EEG2Text models without the constraints of teacher-forcing. The results demonstrate that COFETT significantly enhances the ability to differentiate model performances, paving the way for practical applications in communication restoration for individuals with severe paralysis.
Teacher-forcing-free EEG2Text decoding is not only feasible but also significantly enhances model evaluation, challenging previous assumptions about EEG's linguistic capabilities.
Translating brain signals into text could restore communication for people with severe paralysis, yet practically usable systems to date rely on invasive electrocorticography (ECoG). Electroencephalography (EEG) offers a non-invasive alternative, and EEG-to-text (EEG2Text) has been widely explored. Interestingly, however, EEG2Text models generally rely on teacher-forcing evaluation; without it, they fail to generate meaningful decoding. This reliance prevents EEG2Text from being applied in real-world, non-academic settings. This has fueled numerous debates about whether EEG2Text is a meaningful direction, by extension, and whether EEG truly contains decodable linguistic information. Here, using a neuropsychology-informed paradigm, we find that existing EEG2Text benchmarks have neglected EEG instability, a flaw that has confounded inference and sparked debate. Our experiments furnish key evidence for the feasibility of teacher-forcing-free EEG2Text decoding. Accordingly, we assemble the Corpus OF Eeg-To-Text (COFETT) using a 128-channel high-density EEG cap, providing a benchmark dedicated to evaluating EEG2Text models. In comparisons with multiple existing benchmarks, COFETT achieves SOTA ability to distinguish among model performances and enables robust, teacher-forcing-free evaluation, thereby opening a path toward practical EEG2Text applications. COFETT is open sourced in https://github.com/baoyudu/COFETT.
