发表机构
Meta AI; École Normale Supérieure; Université PSL; CNRS; Hospital Foundation Adolphe de Rothschild; Univ. Lille; Basque Center on Cognition, Brain and Language; Paris Cité University; Inria; Université Paris-Saclay; INSERM; CEA（Meta AI; 高等师范学院; 巴黎文理大学; 法国国家科学研究中心; 阿道夫·德·罗斯柴尔德医院基金会; 里尔大学; 巴斯克认知、大脑与语言中心; 巴黎城市大学; 法国国家信息与自动化研究所; 巴黎萨克雷大学; 法国国家健康与医学研究院; 法国原子能和替代能源委员会）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出Brain2Qwerty v2模型，利用MEG记录解码自然句子，平均WER为39%，准确率随数据量提升，通过AI技术缩小非侵入式与颅内脑机接口的性能差距。
AI 中文摘要
为因脑损伤丧失说话或行动能力的人群恢复沟通能力是一项重大挑战。虽然颅内植入物现已能实现高性能的脑机接口，但非侵入式替代方案仍落后。本文提出Brain2Qwerty v2模型，该模型仅通过实时脑磁图（MEG）记录即可解码自然句子的生成过程。通过收集9名受试者输入的22000个句子，每个受试者记录时长为10小时，我们的模型利用字符、单词和句子层面的表征，实现了39%的平均词错误率（WER）。对于表现最佳的受试者，该模型能准确解码一半的句子，且每个句子的词错误数不超过1个。关键的是，解码准确率随数据量呈对数线性提升，这表明通过数据规模扩展可部分缩小其与颅内方法的性能差距。我们展示了AI从三个主要方面实现这一性能：用深度学习替代手工设计的事件检测流程；微调大型语言模型以提取语义表征；部署AI智能体通过自动化代码开发迭代优化解码流程。综合来看，这些结果表明非侵入式脑-文本解码已达到此前仅属于外科植入物的准确率水平，为安全高效的脑机接口开辟了道路。
英文摘要
Restoring communication for people who have lost the ability to speak or move after a brain injury is a major challenge. While intracranial implants now enable high-performing brain-computer-interfaces, non-invasive alternatives are still lagging behind. Here, we present Brain2Qwerty v2, a model that can decode the production of natural sentences solely from real-time magnetoencephalography (MEG) recordings. By collecting 22,000 sentences typed by nine subjects, each recorded for 10 hours, our model leverages character, word and sentence-level representations to achieve an average word error rate (WER) of 39%. For our best participant, the model accurately decodes half of the sentences with one word error or less. Critically, decoding accuracy log-linearly improves with data volume, suggesting that the performance gap with intracranial approaches could be partially bridged through data scaling. We show that AI enables this performance in three main ways: the substitution of hand-crafted pipelines for event detection with deep learning, the finetuning of large language models to extract semantic representations, and the deployment of AI agents to iteratively refine our decoding pipeline via automated code development. Together, these results show that non-invasive brain-to-text decoding starts to operate at a level of accuracy previously thought exclusive to surgical implants, opening a path toward safe and efficient brain-computer-interfaces.
CommentsMingfang Zhang and Jarod Lévy contributed equally to this work
