基于多尺度注意力时序编码网络的语音诱发脑电解码
姚梓豪,贾海蓉,李雅荣,陈桂军

Speech-evoked EEG decoding based on Multi-scale Attention Temporal Encoding Network
Zihao YAO,Hairong JIA,Yarong LI,Guijun CHEN
表 3 MATE-Net 关键模块对模型性能影响的消融实验结果
Tab.3 Ablation study results on impact of key modules in MATE-Net on model performance
模型结构Acctrain/%ρr
模型1(保留Inception)53.460.6090.634
模型2(保留Inception+残差)63.900.7430.795
模型3(保留Inception+残差+GRU)68.590.8290.893
模型4(MATE-Net)74.300.8840.942