Metraipolis › archive › dc_16eb965ebe97
Integrating Language Models into Listened and Imagined Speech Decoding from MEG — arXiv:2609.31997
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31997
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:36:12.619Z
- SHA-256 of the archived text
c7f35047e22d0757840ccff3a5060e4aafe98449f1919c6dc061c6e7fa4b8d9c- Stable URL of this page
https://metraipolis.com/documento/dc_16eb965ebe97
How to cite
Integrating Language Models into Listened and Imagined Speech Decoding from MEG — arXiv:2609.31997 — arXiv (en), https://arxiv.org/abs/2609.31997 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_16eb965ebe97 (Metraipolis archive dc_16eb965ebe97, sha256 c7f35047e22d0757840ccff3a5060e4aafe98449f1919c6dc061c6e7fa4b8d9c)
BibTeX
@misc{dc16eb965ebe97,
title = {Integrating Language Models into Listened and Imagined Speech Decoding from MEG — arXiv:2609.31997},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31997},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_16eb965ebe97; sha256 c7f35047e22d0757840ccff3a5060e4aafe98449f1919c6dc061c6e7fa4b8d9c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31997. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Decoding imagined speech is an important goal for brain-computer interfaces but remains challenging due to weak neural responses, low signal-to-noise ratio, and limited imagined-speech datasets. Language models provide strong contextual cues for text prediction, but how much they can help neural decoding and whether their contribution differs for decoding perceived and imagined speech remains unclear. To investigate this, we use a paired listened-imagined MEG dataset and incorporate language-model information at two stages. First, we train a contrastive neural decoder that aligns MEG representations with acoustic and contextual language representations, improving cross-subject word decoding for both listened and imagined speech. Second, at inference, we introduce a neural-constrained beam-search framework that combines neural evidence with language-model next-word probabilities. We find that imagined-speech decoding benefits more from the language model than listened-speech decoding. For Imagined speech, the best-performing balance between neural and language-model evidence shifts toward the language model, and the gain over neural-only decoding is larger. Together, these results suggest that language priors are most useful when neural evidence is weaker, making them particularly valuable for imagined-speech BCIs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.31997 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T22:14:27.576Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).