TY - GEN
T1 - Auditory Attention Decoding from EEG using Convolutional Recurrent Neural Network
AU - Fu, Zhen
AU - Wang, Bo
AU - Wu, Xihong
AU - Chen, Jing
N1 - Publisher Copyright:
© 2021 European Signal Processing Conference. All rights reserved.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
KW - Auditory attention decoding
KW - CRNN
KW - Deep neural network
KW - EEG
UR - http://www.scopus.com/inward/record.url?scp=85123216919&partnerID=8YFLogxK
U2 - 10.23919/EUSIPCO54536.2021.9616195
DO - 10.23919/EUSIPCO54536.2021.9616195
M3 - Conference contribution
AN - SCOPUS:85123216919
T3 - European Signal Processing Conference
SP - 970
EP - 974
BT - 29th European Signal Processing Conference, EUSIPCO 2021 - Proceedings
PB - European Signal Processing Conference, EUSIPCO
T2 - 29th European Signal Processing Conference, EUSIPCO 2021
Y2 - 23 August 2021 through 27 August 2021
ER -