ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2505.13446
91
2

Unlocking Non-Invasive Brain-to-Text

19 May 2025
Dulhan Jayalath
Gilad Landau
Oiwi Parker Jones
ArXiv (abs)PDFHTML
Main:9 Pages
10 Figures
Bibliography:4 Pages
9 Tables
Appendix:14 Pages
Abstract

Despite major advances in surgical brain-to-text (B2T), i.e. transcribing speech from invasive brain recordings, non-invasive alternatives have yet to surpass even chance on standard metrics. This remains a barrier to building a non-invasive brain-computer interface (BCI) capable of restoring communication in paralysed individuals without surgery. Here, we present the first non-invasive B2T result that significantly exceeds these critical baselines, raising BLEU by 1.4−2.6×1.4\mathrm{-}2.6\times1.4−2.6× over prior work. This result is driven by three contributions: (1) we extend recent word-classification models with LLM-based rescoring, transforming single-word predictors into closed-vocabulary B2T systems; (2) we introduce a predictive in-filling approach to handle out-of-vocabulary (OOV) words, substantially expanding the effective vocabulary; and (3) we demonstrate, for the first time, how to scale non-invasive B2T models across datasets, unlocking deep learning at scale and improving accuracy by 2.1−2.3×2.1\mathrm{-}2.3\times2.1−2.3×. Through these contributions, we offer new insights into the roles of data quality and vocabulary size. Together, our results remove a major obstacle to realising practical non-invasive B2T systems.

View on arXiv
@article{jayalath2025_2505.13446,
  title={ Unlocking Non-Invasive Brain-to-Text },
  author={ Dulhan Jayalath and Gilad Landau and Oiwi Parker Jones },
  journal={arXiv preprint arXiv:2505.13446},
  year={ 2025 }
}
Comments on this paper