Auditory Attention Decoding from EEG using Convolutional Recurrent Neural Network

Zhen Fu, Bo Wang, Xihong Wu, Jing Chen

科研成果: 书/报告/会议事项章节会议稿件同行评审

7 引用 (Scopus)

摘要

The auditory attention decoding (AAD) approach was proposed to determine the identity of the attended talker in a multi-talker scenario by analyzing electroencephalography (EEG) data. Although the linear model-based method has been widely used in AAD, the linear assumption was considered oversimplified and the decoding accuracy remained lower for shorter decoding windows. Recently, nonlinear models based on deep neural networks (DNN) have been proposed to solve this problem. However, these models did not fully utilize both the spatial and temporal features of EEG, and the interpretability of DNN models was rarely investigated. In this paper, we proposed novel convolutional recurrent neural network (CRNN) based regression model and classification model, and compared them with both the linear model and the state-of-the-art DNN models. Results showed that, our proposed CRNN-based classification model outperformed others for shorter decoding windows (around 90% for 2 s and 5 s). Although worse than classification models, the decoding accuracy of the proposed CRNN-based regression model was about 5% greater than other regression models. The interpretability of DNN models was also investigated by visualizing layers' weight.

源语言英语
主期刊名29th European Signal Processing Conference, EUSIPCO 2021 - Proceedings
出版商European Signal Processing Conference, EUSIPCO
970-974
页数5
ISBN(电子版)9789082797060
DOI
出版状态已出版 - 2021
已对外发布
活动29th European Signal Processing Conference, EUSIPCO 2021 - Dublin, 爱尔兰
期限: 23 8月 202127 8月 2021

出版系列

姓名European Signal Processing Conference
2021-August
ISSN(印刷版)2219-5491

会议

会议29th European Signal Processing Conference, EUSIPCO 2021
国家/地区爱尔兰
Dublin
时期23/08/2127/08/21

指纹

探究 'Auditory Attention Decoding from EEG using Convolutional Recurrent Neural Network' 的科研主题。它们共同构成独一无二的指纹。

引用此