---
title: "Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth"
description: "EEG-to-text (EEG2Text) decoding is a non-invasive alternative to implanted ECoG speech interfaces. 46 references."
authors: ["Zihan Zhang", "Yu Bao", "Xiao Ding", "Tianyi Jiang", "Kai Xiong"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.61/"
doi: "10.18653/v1/2026.acl-long.61"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhang-2026-is-eeg-text-feasible-real/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-is-eeg-text-feasible-real/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/37/) / Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark

# Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark

**Authors:** [Zihan Zhang](https://md.research.elamur.ai/free/en/authors/zihan-zhang/), [Yu Bao](https://md.research.elamur.ai/free/en/authors/yu-bao/), [Xiao Ding](https://md.research.elamur.ai/free/en/authors/xiao-ding/), Tianyi Jiang and [Kai Xiong](https://md.research.elamur.ai/free/en/authors/kai-xiong/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.61/) · [PDF](https://aclanthology.org/2026.acl-long.61.pdf) · [DOI 10.18653/v1/2026.acl-long.61](https://doi.org/10.18653/v1/2026.acl-long.61) · [OpenAlex](https://openalex.org/W7166799362)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
EEG-to-text (EEG2Text) decoding is a non-invasive alternative to implanted ECoG speech interfaces. However, most published systems only look competitive because they are scored with teacher-forcing. When models are not given the gold previous token, their output becomes meaningless, which has led researchers to doubt whether EEG carries recoverable linguistic signal at all. The authors argue that the real problem lies in the benchmarks. Corpora such as ZuCo were built for natural reading and never repeat the same sentence across sessions, so they cannot account for the day-to-day drift of EEG within one person.

To fix this, they built COFETT with a 128-channel high-density cap. Their protocol draws on neuropsychology: participants silently recall sentences, and each sentence is repeated at spaced intervals over eight days. They also swap BLEU for a vector-alignment metric that scores free generation. On this benchmark, models are better separated, and scaling experiments indicate that EEG holds weak but genuine linguistic information. This supports EEG2Text as a viable research direction and points to the need for far more paired data.

## Key points
- **Recording protocol:** 8 days × 4 sessions per day. Each trial has three phases: word-by-word reading, inner-speech recall and rest. The texts cover 39 categories of everyday expressions.
- **Two data parts:** On days 1–4, 1,124 sentences were each recalled 4 times. On days 5–8, 252 sentences were each recalled 16 times.
- **Evaluation:** Teacher-forcing is banned at inference. Outputs are scored by embedding alignment rather than BLEU.
- **Scaling analysis:** The setup pairs the EEGPT encoder with LaBSE text embeddings.
  - Alignment improves both with more sentences and with more repetitions, and the number of sentences matters more.
  - Adding sentences from outside the test domain brings no gain. The authors use this to help explain earlier failures on ZuCo.
- **Data projection:** Reaching translation-like alignment would require about 700 repetitions per sentence, roughly 40× the current amount. Released at github.com/baoyudu/COFETT.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Harbin Institute of Technology](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/) — University, Harbin, China · 185 works · 29,140 citations
- [Nanjing University](https://md.research.elamur.ai/free/en/universities/nanjing-university/) — University, Nanjing, China · 99 works · 8,512 citations
- [Shanghai Innovation Institute](https://md.research.elamur.ai/free/en/universities/shanghai-innovation-institute/) — University, Shanghai, China · 34 works · 325 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,649 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 930 works · [🧠 Neuroscience](https://md.research.elamur.ai/free/en/shelves/neuroscience/) · 186 works · [🧠 Cognitive Neuroscience](https://md.research.elamur.ai/free/en/shelves/neuroscience/cognitive-neuroscience/) · 185 works · [🖱️ Human-Computer Interaction](https://md.research.elamur.ai/free/en/shelves/computer-science/human-computer-interaction/) · 160 works

🧭 Topics (1): [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,341 works

## Cite

Cite as: Zihan Zhang, Yu Bao, Xiao Ding, Tianyi Jiang and Kai Xiong. 2026. Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhang2026is,
  title = {{Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark}},
  author = {Zihan Zhang, Yu Bao, Xiao Ding, Tianyi Jiang and Kai Xiong},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.61},
  url = {https://doi.org/10.18653/v1/2026.acl-long.61}
}
```

- [← previous Is Cross-Lingual Transfer in Bilingual Models Human-Like? A Study with Overlapping Word Forms in Dutch and English](https://md.research.elamur.ai/free/en/papers/skrjanec-2026-is-cross-lingual-transfer-bilingual/)
- [next → Is Micro Domain-Adaptive Pre-Training Effective for Real-World Operations? Multi-Step Evaluation Reveals Potential and Bottlenecks](https://md.research.elamur.ai/free/en/papers/tsunokake-2026-is-micro-domain-adaptive-pre/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/37/)

## References

46 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mahnaz Arvaneh, Cuntai Guan, Kai Keng Ang, and Chai Quek. 2013. Eeg data space adaptation to reduce intersession nonstationarity in brain-computer interface. Neural computation, 25(8):2146–2171. [find](https://scholar.google.com/scholar?q=Mahnaz+Arvaneh%2C+Cuntai+Guan%2C+Kai+Keng+Ang%2C+and+Chai+Quek%2E+2013%2E+Eeg+data+space+adaptation+to+reduce+intersession+nonstationarity+in+brain%2Dcomputer+interface%2E+Neural+computation%2C+25%288%29%3A2146%E2%80%932171%2E)
2. Ashutosh Bajpai and Tanmoy Chakraborty. 2024. Multilingual llms inherently reward in-language time-sensitive semantic alignment for low-resource languages. arXiv preprint arXiv:2412.08090. — [arXiv:2412.08090](https://arxiv.org/abs/2412.08090) [find](https://scholar.google.com/scholar?q=Ashutosh+Bajpai+and+Tanmoy+Chakraborty%2E+2024%2E+Multilingual+llms+inherently+reward+in%2Dlanguage+time%2Dsensitive+semantic+alignment+for+low%2Dresource+languages%2E+arXiv+preprint+arXiv%3A2412%2E08090%2E+%E2%80%94+%5BarXiv%3A24)
3. William Bechtel and Leonardo Bich. 2024. Situating homeostasis in organisms: maintaining organization through time. The Journal of Physiology, 602(22):6003–6020. [find](https://scholar.google.com/scholar?q=William+Bechtel+and+Leonardo+Bich%2E+2024%2E+Situating+homeostasis+in+organisms%3A+maintaining+organization+through+time%2E+The+Journal+of+Physiology%2C+602%2822%29%3A6003%E2%80%936020%2E)
4. Nathan E Crone, Amir Sinai, and Anna Korzeniewska. 2006. High-frequency gamma oscillations and human brain mapping with electrocorticography. Progress in Brain Research, 159:275–295. [find](https://scholar.google.com/scholar?q=Nathan+E+Crone%2C+Amir+Sinai%2C+and+Anna+Korzeniewska%2E+2006%2E+High%2Dfrequency+gamma+oscillations+and+human+brain+mapping+with+electrocorticography%2E+Progress+in+Brain+Research%2C+159%3A275%E2%80%93295%2E)
5. Jacek P Dmochowski, Paul Sajda, Joao Dias, and Lucas C Parra. 2012. Correlated components of ongoing eeg point to emotionally laden attention–a possible marker of engagement? Frontiers in human neuroscience, 6:112. [find](https://scholar.google.com/scholar?q=Jacek+P+Dmochowski%2C+Paul+Sajda%2C+Joao+Dias%2C+and+Lucas+C+Parra%2E+2012%2E+Correlated+components+of+ongoing+eeg+point+to+emotionally+laden+attention%E2%80%93a+possible+marker+of+engagement%3F+Frontiers+in+human+neuros)
6. John E Downey, Nathaniel Schwed, Steven M Chase, Andrew B Schwartz, and Jennifer L Collinger. 2018. Intracortical recording stability in human brain– computer interface users. Journal of neural engineering, 15(4):046016. [find](https://scholar.google.com/scholar?q=John+E+Downey%2C+Nathaniel+Schwed%2C+Steven+M+Chase%2C+Andrew+B+Schwartz%2C+and+Jennifer+L+Collinger%2E+2018%2E+Intracortical+recording+stability+in+human+brain%E2%80%93+computer+interface+users%2E+Journal+of+neural+engine)
7. Yiqun Duan, Jinzhao Zhou, Zhen Wang, Yu-Kai Wang, and Chin-teng Lin. 2023. Dewave: Discrete encoding of eeg waves for eeg to text translation. Advances in Neural Information Processing Systems, 36:9907–9918. [find](https://scholar.google.com/scholar?q=Yiqun+Duan%2C+Jinzhao+Zhou%2C+Zhen+Wang%2C+Yu%2DKai+Wang%2C+and+Chin%2Dteng+Lin%2E+2023%2E+Dewave%3A+Discrete+encoding+of+eeg+waves+for+eeg+to+text+translation%2E+Advances+in+Neural+Information+Processing+Systems%2C+36%3A990)
8. Jin Fan, Bruce D McCandliss, Tobias Sommer, Amir Raz, and Michael I Posner. 2002. Testing the efficiency and independence of attentional networks. Journal of cognitive neuroscience, 14(3):340–347. [find](https://scholar.google.com/scholar?q=Jin+Fan%2C+Bruce+D+McCandliss%2C+Tobias+Sommer%2C+Amir+Raz%2C+and+Michael+I+Posner%2E+2002%2E+Testing+the+efficiency+and+independence+of+attentional+networks%2E+Journal+of+cognitive+neuroscience%2C+14%283%29%3A340%E2%80%93347%2E)
9. Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan, and Wei Wang. 2022. [Language-agnostic BERT sentence embedding](https://md.research.elamur.ai/free/en/papers/feng-2020-language-agnostic-bert-sentence-embedding/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 878–891, Dublin, Ireland. Association for Computation…
10. Xiachong Feng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2023. Aligning semantic in brain and language: A curriculum contrastive method for electroencephalography-to-text generation. IEEE Transactions on Neural Systems and Rehabilitation Engineering. [find](https://scholar.google.com/scholar?q=Xiachong+Feng%2C+Xiaocheng+Feng%2C+Bing+Qin%2C+and+Ting+Liu%2E+2023%2E+Aligning+semantic+in+brain+and+language%3A+A+curriculum+contrastive+method+for+electroencephalography%2Dto%2Dtext+generation%2E+IEEE+Transactions+o)
11. Alexandre Gramfort, Martin Luessi, Eric Larson, Denis A Engemann, Daniel Strohmeier, Christian Brodbeck, Lauri Parkkonen, and Matti S Hämäläinen. 2014. Mne software for processing meg and eeg data. neuroimage, 86:446–460. [find](https://scholar.google.com/scholar?q=Alexandre+Gramfort%2C+Martin+Luessi%2C+Eric+Larson%2C+Denis+A+Engemann%2C+Daniel+Strohmeier%2C+Christian+Brodbeck%2C+Lauri+Parkkonen%2C+and+Matti+S+H%C3%A4m%C3%A4l%C3%A4inen%2E+2014%2E+Mne+software+for+processing+meg+and+eeg+data%2E+ne)
12. Tom Henighan, Jared Kaplan, Mor Katz, Mark Chen, Christopher Hesse, Jacob Jackson, Heewoo Jun, Tom B Brown, Prafulla Dhariwal, Scott Gray, and 1 others. 2020. [Scaling laws for autoregressive generative modeling](https://md.research.elamur.ai/free/en/papers/henighan-2020-scaling-laws-autoregressive-generative-modeling/). arXiv preprint arXiv:2010.14701.
13. Gregory Hickok and David Poeppel. 2007. The cortical organization of speech processing. Nature reviews neuroscience, 8(5):393–402. [find](https://scholar.google.com/scholar?q=Gregory+Hickok+and+David+Poeppel%2E+2007%2E+The+cortical+organization+of+speech+processing%2E+Nature+reviews+neuroscience%2C+8%285%29%3A393%E2%80%93402%2E)
14. Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, and 1 others. 2022. [Training compute-optimal large language models](https://md.research.elamur.ai/free/en/papers/hoffmann-2022-training-compute-optimal-large-language/). arXiv preprint arXiv:2203.15556.
15. Nora Hollenstein, Jonathan Rotsztejn, Marius Troendle, Andreas Pedroni, Ce Zhang, and Nicolas Langer. 2018. Zuco, a simultaneous eeg and eye-tracking resource for natural sentence reading. Scientific data, 5(1):1–13. [find](https://scholar.google.com/scholar?q=Nora+Hollenstein%2C+Jonathan+Rotsztejn%2C+Marius+Troendle%2C+Andreas+Pedroni%2C+Ce+Zhang%2C+and+Nicolas+Langer%2E+2018%2E+Zuco%2C+a+simultaneous+eeg+and+eye%2Dtracking+resource+for+natural+sentence+reading%2E+Scientific+)
16. Nora Hollenstein, Marius Troendle, Ce Zhang, and Nicolas Langer. 2019. Zuco 2.0: A dataset of physiological recordings during natural reading and annotation. arXiv preprint arXiv:1912.00903. [find](https://scholar.google.com/scholar?q=Nora+Hollenstein%2C+Marius+Troendle%2C+Ce+Zhang%2C+and+Nicolas+Langer%2E+2019%2E+Zuco+2%2E0%3A+A+dataset+of+physiological+recordings+during+natural+reading+and+annotation%2E+arXiv+preprint+arXiv%3A1912%2E00903%2E)
17. Aapo Hyvärinen. 1997. Independent component analysis by minimization of mutual information. [find](https://scholar.google.com/scholar?q=Aapo+Hyv%C3%A4rinen%2E+1997%2E+Independent+component+analysis+by+minimization+of+mutual+information%2E)
18. Mainak Jas, Denis A Engemann, Yousra Bekhti, Federico Raimondo, and Alexandre Gramfort. 2017. Autoreject: Automated artifact rejection for meg and eeg data. NeuroImage, 159:417–429. [find](https://scholar.google.com/scholar?q=Mainak+Jas%2C+Denis+A+Engemann%2C+Yousra+Bekhti%2C+Federico+Raimondo%2C+and+Alexandre+Gramfort%2E+2017%2E+Autoreject%3A+Automated+artifact+rejection+for+meg+and+eeg+data%2E+NeuroImage%2C+159%3A417%E2%80%93429%2E)
19. Hyejeong Jo, Yiqian Yang, Juhyeok Han, Yiqun Duan, Hui Xiong, and Won Hee Lee. 2024. Are eeg-to-text models working? arXiv preprint arXiv:2405.06459. — [arXiv:2405.06459](https://arxiv.org/abs/2405.06459) [find](https://scholar.google.com/scholar?q=Hyejeong+Jo%2C+Yiqian+Yang%2C+Juhyeok+Han%2C+Yiqun+Duan%2C+Hui+Xiong%2C+and+Won+Hee+Lee%2E+2024%2E+Are+eeg%2Dto%2Dtext+models+working%3F+arXiv+preprint+arXiv%3A2405%2E06459%2E+%E2%80%94+%5BarXiv%3A2405%2E06459%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2405%2E06)
20. Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. [Scaling laws for neural language models](https://md.research.elamur.ai/free/en/papers/kaplan-2020-scaling-laws-neural-language-models/). arXiv preprint arXiv:2001.08361.
21. Vernon J Lawhern, Amelia J Solon, Nicholas R Waytowich, Stephen M Gordon, Chou P Hung, and Brent J Lance. 2018. Eegnet: a compact convolutional neural network for eeg-based brain–computer interfaces. Journal of neural engineering, 15(5):056013. [find](https://scholar.google.com/scholar?q=Vernon+J+Lawhern%2C+Amelia+J+Solon%2C+Nicholas+R+Waytowich%2C+Stephen+M+Gordon%2C+Chou+P+Hung%2C+and+Brent+J+Lance%2E+2018%2E+Eegnet%3A+a+compact+convolutional+neural+network+for+eeg%2Dbased+brain%E2%80%93computer+interfaces%2E+)
22. Seo-Hyun Lee, Minji Lee, and Seong-Whan Lee. 2020. Neural decoding of imagined speech and visual imagery as intuitive paradigms for bci communication. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 28(12):2647–2659. [find](https://scholar.google.com/scholar?q=Seo%2DHyun+Lee%2C+Minji+Lee%2C+and+Seong%2DWhan+Lee%2E+2020%2E+Neural+decoding+of+imagined+speech+and+visual+imagery+as+intuitive+paradigms+for+bci+communication%2E+IEEE+Transactions+on+Neural+Systems+and+Rehabilit)
23. Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. [Dailydialog: A manually labelled multi-turn dialogue dataset](https://md.research.elamur.ai/free/en/papers/li-2017-dailydialog-manually-labelled-multi-turn/). In Proceedings of the Eighth International Joint Conference on Natural Language Processing (IJCNLP).
24. Nasrin Mostafazadeh, Nathanael Chambers, Xiaodong He, Devi Parikh, Dhruv Batra, Lucy Vanderwende, Pushmeet Kohli, and James Allen. 2016. A corpus and cloze evaluation for deeper understanding of commonsense stories. In Proceedings of the 2016 Conference of the North American Chapter of the Associati… [find](https://scholar.google.com/scholar?q=Nasrin+Mostafazadeh%2C+Nathanael+Chambers%2C+Xiaodong+He%2C+Devi+Parikh%2C+Dhruv+Batra%2C+Lucy+Vanderwende%2C+Pushmeet+Kohli%2C+and+James+Allen%2E+2016%2E+A+corpus+and+cloze+evaluation+for+deeper+understanding+of+commo)
25. Xinyu Mou, Cuilin He, Liwei Tan, Junjie Yu, Huadong Liang, Jianyu Zhang, Yan Tian, Yu-Fang Yang, Ting Xu, Qing Wang, and 1 others. 2024. Chineseeeg: A chinese linguistic corpora eeg dataset for semantic alignment and neural decoding. Scientific Data, 11(1):550. [find](https://scholar.google.com/scholar?q=Xinyu+Mou%2C+Cuilin+He%2C+Liwei+Tan%2C+Junjie+Yu%2C+Huadong+Liang%2C+Jianyu+Zhang%2C+Yan+Tian%2C+Yu%2DFang+Yang%2C+Ting+Xu%2C+Qing+Wang%2C+and+1+others%2E+2024%2E+Chineseeeg%3A+A+chinese+linguistic+corpora+eeg+dataset+for+semant)
26. Saydul Akbar Murad and Nick Rahimi. 2024. Unveiling thoughts: A review of advancements in eeg brain signal decoding into text. IEEE Transactions on Cognitive and Developmental Systems. [find](https://scholar.google.com/scholar?q=Saydul+Akbar+Murad+and+Nick+Rahimi%2E+2024%2E+Unveiling+thoughts%3A+A+review+of+advancements+in+eeg+brain+signal+decoding+into+text%2E+IEEE+Transactions+on+Cognitive+and+Developmental+Systems%2E)
27. Nicolás Nieto, Victoria Peterson, Hugo Leonardo Rufiner, Juan Esteban Kamienkowski, and Ruben Spies. 2022. Thinking out loud, an open-access eeg-based bci dataset for inner speech recognition. Scientific Data, 9(1):52. [find](https://scholar.google.com/scholar?q=Nicol%C3%A1s+Nieto%2C+Victoria+Peterson%2C+Hugo+Leonardo+Rufiner%2C+Juan+Esteban+Kamienkowski%2C+and+Ruben+Spies%2E+2022%2E+Thinking+out+loud%2C+an+open%2Daccess+eeg%2Dbased+bci+dataset+for+inner+speech+recognition%2E+Scienti)
28. Harry Nyquist. 1928. Certain topics in telegraph transmission theory. Transactions of the American Institute of Electrical Engineers, 47(2):617–644. [find](https://scholar.google.com/scholar?q=Harry+Nyquist%2E+1928%2E+Certain+topics+in+telegraph+transmission+theory%2E+Transactions+of+the+American+Institute+of+Electrical+Engineers%2C+47%282%29%3A617%E2%80%93644%2E)
29. Jonathan W Peirce, Jeremy R Gray, Samuel Simpson, Max R MacAskill, Richard Höchenberger, Hiroyuki Sogo, Erik Kastman, and Jonas K Lindeløv. 2019. Psychopy2: experiments in behavior made easy. Behavior Research Methods, 51(1):195–203. [find](https://scholar.google.com/scholar?q=Jonathan+W+Peirce%2C+Jeremy+R+Gray%2C+Samuel+Simpson%2C+Max+R+MacAskill%2C+Richard+H%C3%B6chenberger%2C+Hiroyuki+Sogo%2C+Erik+Kastman%2C+and+Jonas+K+Lindel%C3%B8v%2E+2019%2E+Psychopy2%3A+experiments+in+behavior+made+easy%2E+Behavior)
30. Timothée Proix, Jaime Delgado Saa, Andy Christen, Stephanie Martin, Brian N Pasley, Robert T Knight, Xing Tian, David Poeppel, Werner K Doyle, Orrin Devinsky, and 1 others. 2022. Imagined speech can be decoded from low-and cross-frequency intracranial eeg features. Nature communications, 13(1):48. [find](https://scholar.google.com/scholar?q=Timoth%C3%A9e+Proix%2C+Jaime+Delgado+Saa%2C+Andy+Christen%2C+Stephanie+Martin%2C+Brian+N+Pasley%2C+Robert+T+Knight%2C+Xing+Tian%2C+David+Poeppel%2C+Werner+K+Doyle%2C+Orrin+Devinsky%2C+and+1+others%2E+2022%2E+Imagined+speech+can+b)
31. Tsam Kiu Pun, Mona Khoshnevis, Tommy Hosman, Guy H Wilson, Anastasia Kapitonava, Foram Kamdar, Jaimie M Henderson, John D Simeral, Carlos E Vargas-Irwin, Matthew T Harrison, and 1 others. 2024. Measuring instability in chronic human intracortical neural recordings towards stable, long-term brain-com… [find](https://scholar.google.com/scholar?q=Tsam+Kiu+Pun%2C+Mona+Khoshnevis%2C+Tommy+Hosman%2C+Guy+H+Wilson%2C+Anastasia+Kapitonava%2C+Foram+Kamdar%2C+Jaimie+M+Henderson%2C+John+D+Simeral%2C+Carlos+E+Vargas%2DIrwin%2C+Matthew+T+Harrison%2C+and+1+others%2E+2024%2E+Measur)
32. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). Journal of machine learning research, 21(140):1–67.
33. Wojciech Samek, Carmen Vidaurre, Klaus-Robert Müller, and Motoaki Kawanabe. 2012. Stationary common spatial patterns for brain–computer interfacing. Journal of neural engineering, 9(2):026013. [find](https://scholar.google.com/scholar?q=Wojciech+Samek%2C+Carmen+Vidaurre%2C+Klaus%2DRobert+M%C3%BCller%2C+and+Motoaki+Kawanabe%2E+2012%2E+Stationary+common+spatial+patterns+for+brain%E2%80%93computer+interfacing%2E+Journal+of+neural+engineering%2C+9%282%29%3A026013%2E)
34. Alexander B Silva, Kaylo T Littlejohn, Jessie R Liu, David A Moses, and Edward F Chang. 2024. The speech neuroprosthesis. Nature Reviews Neuroscience, 25(7):473–492. [find](https://scholar.google.com/scholar?q=Alexander+B+Silva%2C+Kaylo+T+Littlejohn%2C+Jessie+R+Liu%2C+David+A+Moses%2C+and+Edward+F+Chang%2E+2024%2E+The+speech+neuroprosthesis%2E+Nature+Reviews+Neuroscience%2C+25%287%29%3A473%E2%80%93492%2E)
35. Yonghao Song, Qingqing Zheng, Bingchuan Liu, and Xiaorong Gao. 2022. Eeg conformer: Convolutional transformer for eeg decoding and visualization. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31:710–719. [find](https://scholar.google.com/scholar?q=Yonghao+Song%2C+Qingqing+Zheng%2C+Bingchuan+Liu%2C+and+Xiaorong+Gao%2E+2022%2E+Eeg+conformer%3A+Convolutional+transformer+for+eeg+decoding+and+visualization%2E+IEEE+Transactions+on+Neural+Systems+and+Rehabilitation)
36. Yi-Yuan Tang, Yinghua Ma, Junhong Wang, Yaxin Fan, Shigang Feng, Qilin Lu, Qingbao Yu, Danni Sui, Mary K Rothbart, Ming Fan, and 1 others. 2007. Short-term meditation training improves attention and self-regulation. Proceedings of the national Academy of Sciences, 104(43):17152–17156. [find](https://scholar.google.com/scholar?q=Yi%2DYuan+Tang%2C+Yinghua+Ma%2C+Junhong+Wang%2C+Yaxin+Fan%2C+Shigang+Feng%2C+Qilin+Lu%2C+Qingbao+Yu%2C+Danni+Sui%2C+Mary+K+Rothbart%2C+Ming+Fan%2C+and+1+others%2E+2007%2E+Short%2Dterm+meditation+training+improves+attention+and+s)
37. Xing Tian and David Poeppel. 2010. Mental imagery of speech and movement implicates the dynamics of internal forward models. Frontiers in psychology, 1:7029. [find](https://scholar.google.com/scholar?q=Xing+Tian+and+David+Poeppel%2E+2010%2E+Mental+imagery+of+speech+and+movement+implicates+the+dynamics+of+internal+forward+models%2E+Frontiers+in+psychology%2C+1%3A7029%2E)
38. Guangyu Wang, Wenchao Liu, Yuhong He, Cong Xu, Lin Ma, and Haifeng Li. 2024a. Eegpt: Pretrained transformer for universal and reliable representation of eeg signals. Advances in Neural Information Processing Systems, 37:39249–39280. [find](https://scholar.google.com/scholar?q=Guangyu+Wang%2C+Wenchao+Liu%2C+Yuhong+He%2C+Cong+Xu%2C+Lin+Ma%2C+and+Haifeng+Li%2E+2024a%2E+Eegpt%3A+Pretrained+transformer+for+universal+and+reliable+representation+of+eeg+signals%2E+Advances+in+Neural+Information+Pro)
39. Jiaqi Wang, Zhenxi Song, Zhengyu Ma, Xipeng Qiu, Min Zhang, and Zhiguo Zhang. 2024b. Enhancing eeg-to-text decoding through transferable representations from pre-trained contrastive eeg-text masked autoencoder. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistic… [find](https://scholar.google.com/scholar?q=Jiaqi+Wang%2C+Zhenxi+Song%2C+Zhengyu+Ma%2C+Xipeng+Qiu%2C+Min+Zhang%2C+and+Zhiguo+Zhang%2E+2024b%2E+Enhancing+eeg%2Dto%2Dtext+decoding+through+transferable+representations+from+pre%2Dtrained+contrastive+eeg%2Dtext+masked+au)
40. Zhenhailong Wang and Heng Ji. 2022. Open vocabulary electroencephalography-to-text decoding and zero-shot sentiment classification. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 5350–5358. [find](https://scholar.google.com/scholar?q=Zhenhailong+Wang+and+Heng+Ji%2E+2022%2E+Open+vocabulary+electroencephalography%2Dto%2Dtext+decoding+and+zero%2Dshot+sentiment+classification%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+vo)
41. Francis R Willett, Erin M Kunz, Chaofei Fan, Donald T Avansino, Guy H Wilson, Eun Young Choi, Foram Kamdar, Matthew F Glasser, Leigh R Hochberg, Shaul Druckmann, and 1 others. 2023. A high-performance speech neuroprosthesis. Nature, 620(7976):1031–1036. [find](https://scholar.google.com/scholar?q=Francis+R+Willett%2C+Erin+M+Kunz%2C+Chaofei+Fan%2C+Donald+T+Avansino%2C+Guy+H+Wilson%2C+Eun+Young+Choi%2C+Foram+Kamdar%2C+Matthew+F+Glasser%2C+Leigh+R+Hochberg%2C+Shaul+Druckmann%2C+and+1+others%2E+2023%2E+A+high%2Dperformance)
42. Ronald J Williams and David Zipser. 1989. A learning algorithm for continually running fully recurrent neural networks. Neural computation, 1(2):270–280. [find](https://scholar.google.com/scholar?q=Ronald+J+Williams+and+David+Zipser%2E+1989%2E+A+learning+algorithm+for+continually+running+fully+recurrent+neural+networks%2E+Neural+computation%2C+1%282%29%3A270%E2%80%93280%2E)
43. Nuwa Xi, Sendong Zhao, Haochun Wang, Chi Liu, Bing Qin, and Ting Liu. 2023. [Unicorn: Unified cognitive signal reconstruction bridging cognitive signals and human language](https://md.research.elamur.ai/free/en/papers/xi-2023-unicorn-unified-cognitive-signal-reconstruction/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13277–…
44. Jingqing Zhang, Yao Zhao, Mohammad Saleh, and Peter Liu. 2020. [Pegasus: Pre-training with extracted gap-sentences for abstractive summarization](https://md.research.elamur.ai/free/en/papers/zhang-2019-pegasus-pre-training-extracted-gap/). In International conference on machine learning, pages 11328–11339. PMLR.
45. Zihan Zhang, Xiao Ding, Yu Bao, Yi Zhao, Xia Liang, Bing Qin, and Ting Liu. 2024. Chisco: An eeg-based bci dataset for decoding of imagined speech. Scientific Data, 11(1):1265. [find](https://scholar.google.com/scholar?q=Zihan+Zhang%2C+Xiao+Ding%2C+Yu+Bao%2C+Yi+Zhao%2C+Xia+Liang%2C+Bing+Qin%2C+and+Ting+Liu%2E+2024%2E+Chisco%3A+An+eeg%2Dbased+bci+dataset+for+decoding+of+imagined+speech%2E+Scientific+Data%2C+11%281%29%3A1265%2E)
46. Jinzhao Zhou, Yiqun Duan, Yu-Cheng Chang, Yu-Kai Wang, and Chin-Teng Lin. 2024. Belt: bootstrapped eeg-to-language training by natural language supervision. IEEE Transactions on Neural Systems and Rehabilitation Engineering. [find](https://scholar.google.com/scholar?q=Jinzhao+Zhou%2C+Yiqun+Duan%2C+Yu%2DCheng+Chang%2C+Yu%2DKai+Wang%2C+and+Chin%2DTeng+Lin%2E+2024%2E+Belt%3A+bootstrapped+eeg%2Dto%2Dlanguage+training+by+natural+language+supervision%2E+IEEE+Transactions+on+Neural+Systems+and+Reh)

*Updated 2 November 2026*