用脑电波解码打字意图，实现非侵入式文字生成。
Brain-to-Text Decoding: A Non-invasive Approach via Typing
- 基于EEG/MEG信号，用深度学习模型解码打字时的脑活动
- 使用MEG时字符错误率低至32%，最佳者仅19%
- 适合神经康复患者，为安全脑机接口提供新路径
现代神经假体已能恢复丧失言语或运动能力患者的沟通能力，但侵入式设备存在神经外科固有风险。本文提出一种非侵入式方法，通过脑活动解码句子生成，并在35名健康志愿者中验证其有效性。我们设计了Brain2Qwerty模型，利用参与者在键盘上打字时采集的脑电（EEG）或脑磁（MEG）信号进行训练。结果表明，使用MEG时，平均字符错误率（CER）为32%，显著优于EEG（CER: 67%）；表现最佳者达到CER 19%，并能准确解码训练集外的多种句子。错误分析显示，解码依赖运动过程，但打字错误特征也反映高层认知因素。该成果缩小了侵入式与非侵入式方法的差距，为非沟通患者开发安全脑机接口铺平道路。
原文摘要 · Abstract (English)
Modern neuroprostheses can now restore communication in patients who have lost the ability to speak or move. However, these invasive devices entail risks inherent to neurosurgery. Here, we introduce a non-invasive method to decode the production of sentences from brain activity and demonstrate its efficacy in a cohort of 35 healthy volunteers. For this, we present Brain2Qwerty, a new deep learning architecture trained to decode sentences from either electro- (EEG) or magneto-encephalography (MEG), while participants typed briefly memorized sentences on a QWERTY keyboard. With MEG, Brain2Qwerty reaches, on average, a character-error-rate (CER) of 32% and substantially outperforms EEG (CER: 67%). For the best participants, the model achieves a CER of 19%, and can perfectly decode a variety of sentences outside of the training set. While error analyses suggest that decoding depends on motor processes, the analysis of typographical errors suggests that it also involves higher-level cognitive factors. Overall, these results narrow the gap between invasive and non-invasive methods and thus open the path for developing safe brain-computer interfaces for non-communicating patients.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。