Year: 2026
Type: preprint
Abstract: Decoding perceived language from non-invasive magnetoencephalography (MEG) offers a promising route toward brain-to-text communication. NeuSpeech first introduces Whisper to MEG-to-text decoding, while BrainECHO improves its accuracy through acoustic reconstruction. However, whether further accuracy gains can be achieved without relying on additional acoustic supervision remains unclear. Here, we propose MEGWeaver, a framework for direct MEG-to-text generation that pretrains a MEG encoder based on sentence relational pretraining (SRP), which aligns the in-batch similarity structure of MEG representations with sentence-level relations defined by similarities between embeddings from a frozen sentence encoder. Only the pretrained sensor projection is transferred to downstream text decoding. Across English, Dutch and Chinese datasets under held-out-participant evaluation, MEGWeaver achieves BLEU-4 scores of $75.10\pm1.21$, $48.78\pm1.17$ and $39.07\pm0.72$, respectively, outperforming NeuSpeech and sentence retrieval across all three datasets and obtaining numerically higher BLEU-4 than our BrainECHO reproduction on Dutch and Chinese. These findings support direct MEG-to-text generation for known sentences under the present segmentation protocol, while decoding novel sentences remains an open problem.
Institutions: East China Normal University, Northeastern University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Keywords: brain-computer interface, neuromodulation
Open Access status: green
OpenAlex ID: W7235795714
