从分钟到天：通过监督预训练扩展颅内语音解码
From Minutes to Days: Scaling Intracranial Speech Decoding with Supervised Pretraining
AI总结：
通过监督预训练扩展颅内语音解码，利用长期数据提升解码性能并解决跨天变化问题。
摘要：
从大脑活动解码语音通常依赖于在短而高度受控的实验中收集的有限神经记录。在这里，我们介绍了一个框架，利用患者接受临床监测时获取的周长颅内和音频记录，有效将训练数据集的规模增加超过两个数量级。借助这种预训练，我们的对比学习模型在仅使用传统实验数据训练的模型上表现显著更好，其提升幅度与数据集规模呈对数线性关系。对学习表示的分析显示，尽管大脑活动代表语音特征，但其整体结构在不同天之间大幅漂移，突显了需要明确考虑跨天变化的模型的必要性。总体而言，我们的方法为在现实生活和受控任务设置中解码和建模大脑表示开辟了可扩展的道路。
英文摘要：
Decoding speech from brain activity has typically relied on limited neural recordings collected during short and highly controlled experiments. Here, we introduce a framework to leverage week-long intracranial and audio recordings from patients undergoing clinical monitoring, effectively increasing the training dataset size by over two orders of magnitude. With this pretraining, our contrastive learning model substantially outperforms models trained solely on classic experimental data, with gains that scale log-linearly with dataset size. Analysis of the learned representations reveals that, while brain activity represents speech features, its global structure largely drifts across days, highlighting the need for models that explicitly account for cross-day variability. Overall, our approach opens a scalable path toward decoding and modeling brain representations in both real-life and controlled task settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
