利用词边界增强EEG语音匹配与不匹配任务
Enhancing the EEG Speech Match Mismatch Tasks With Word Boundaries
AI总结：
本研究针对大脑对语音的离散处理问题，提出在EEG与语音匹配-不匹配分类任务中引入词边界信息，通过卷积网络、基于词边界的平均池化及循环层提取特征，将分类准确率从65-75%显著提升至93%。
摘要：
近期研究表明，通过语音刺激与神经反应的匹配-不匹配分类，可以分析人类语音理解的神经机制。然而，这些研究均针对固定时长片段，未考虑大脑对语音的离散处理。在本研究中，我们通过将EEG与语音输入相关联，证实了词边界信息在句子处理中具有重要作用。我们使用卷积层网络处理语音和EEG信号。随后，对特征表示执行基于词边界的平均池化，并利用循环层整合词间上下文。实验表明，在公开的语音-EEG数据集上，建模准确率（匹配-不匹配分类准确率）可显著提升至93%，而此前该任务的准确率仅为65-75%。
英文摘要：
Recent studies have shown that the underlying neural mechanisms of human speech comprehension can be analyzed using a match-mismatch classification of the speech stimulus and the neural response. However, such studies have been conducted for fixed-duration segments without accounting for the discrete processing of speech in the brain. In this work, we establish that word boundary information plays a significant role in sentence processing by relating EEG to its speech input. We process the speech and the EEG signals using a network of convolution layers. Then, a word boundary-based average pooling is performed on the representations, and the inter-word context is incorporated using a recurrent layer. The experiments show that the modeling accuracy can be significantly improved (match-mismatch classification accuracy) to 93% on a publicly available speech-EEG data set, while previous efforts achieved an accuracy of 65-75% for this task.
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。
