The first non-invasive brain-to-text system exceeds chance baselines on six metrics by combining LLM-based rescoring, out-of-vocabulary in-filling, and selective pooling of MEG/EEG datasets.
A streaming brain-to-voice neuroprosthesis to restore naturalistic communication
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Unlocking Non-Invasive Brain-to-Text
The first non-invasive brain-to-text system exceeds chance baselines on six metrics by combining LLM-based rescoring, out-of-vocabulary in-filling, and selective pooling of MEG/EEG datasets.