Code for paper: DBPNet: Dual-Branch Parallel Network with Temporal-Frequency Fusion for Auditory Attention Detection
This paper introduces DBPNet, a novel AAD network that integrates temporal and frequency domains to enhance EEG signal decoding.
Qinke Ni, Hongyu Zhang, Shengbing Pei, Chang Zhou, Zhao Lv, Cunhang Fan. DBPNet: Dual-Branch Parallel Network with Temporal-Frequency Fusion for Auditory Attention Detection. In Ijcai 2024.
- Please download the AAD dataset for training.
- The public KUL dataset, DTU dataset and MM-AAD(not yet open) are used in this paper.
- Python3.11.4
pip install -r requirements.txt
- Modify the
args.*
variable in model.py to match the dataset - Using model.py to train and test the model
- Using multi_processing.py to train and test the model in parallel