mlsanityData to 14 Oct 2026

Unlocking Non-Invasive Brain-to-Text

arXiv 2505.13446 ↗First posted 19 May 2025cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

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× 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×. 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.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 19 of its 46 references that are in the map. First posted on arXiv 19 May 2025.

Builds on

19 of 46 references.

References · 19

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  5. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  6. 2024Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCIcited by 327
  7. 2021BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG datacited by 199
  8. 2022Decoding speech perception from non-invasive brain recordingscited by 130
  9. 2021Open Vocabulary Electroencephalography-To-Text Decoding and Zero-shot Sentiment Classificationcited by 67
  10. 2024Are EEG-to-Text Models Working?cited by 32
  11. 2025Brain-to-Text Decoding: A Non-invasive Approach via Typingcited by 22
  12. 2024The Brain's Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learningcited by 21
7 more
  1. 2024emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyographycited by 18
  2. 2024MAD: Multi-Alignment MEG-to-Text Decodingcited by 15
  3. 2024Decoding individual words from non-invasive brain recordings across 723 participantscited by 13
  4. 2024NeuSpeech: Decode Neural signal as Speechcited by 11
  5. 2024NeuGPT: Unified multi-modal Neural GPTcited by 7
  6. 2024Resolving Domain Shift For Representations Of Speech In Non-Invasive Brain Recordingscited by 5
  7. 2024Non-invasive Neural Decoding in Source Reconstructed Brain Spacecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 9.

15 papers.

Sort:

By area:

  1. 2025LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scalecited by 20
  2. 2025The 2025 PNPL Competition: Speech Detection and Phoneme Classification in the LibriBrain Datasetcited by 17
  3. 2026MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Trainingcited by 7
  4. 2025Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologiescited by 5
  5. 2026LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scalecited by 5
  6. 2025MEGConformer: Conformer-Based MEG Decoder for Robust Speech and Phoneme Classificationcited by 4
  7. 2025Elementary, My Dear Watson: Non-Invasive Neural Keyword Spotting in the LibriBrain Datasetcited by 3
  8. 2026What Are We Actually Decoding? Source Attribution for Non-Invasive Brain-to-Language Retrievalcited by 3
  9. 2026A Common Measure of Communication for Speech Brain-Computer Interfacescited by 3
  10. 2026The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100cited by 2
  11. 2025From Minutes to Days: Scaling Intracranial Speech Decoding with Supervised Pretrainingcited by 1
  12. 2026Brain-to-Language Decoding: Tasks, Signals, Methods, Evaluation, Practical Use and Beyondcited by 1
3 more
  1. 2026MEG-to-MEG Transfer Learning and Cross-Task Speech/Silence Detection with Limited Datacited by 0
  2. 2026MeGA-MP: Metric Graph Advection Message Passing -- A Physics-Informed Message Passing Operator for Advection-Dominated Metric Graphscited by 0
  3. 2026Removing Timing Shortcuts Improves Non-Invasive Brain-to-Textcited by 0