PyTorch implementation for the paper:
-
Title: Audio-Visual Domain Adaptation Feature Fusion for Speech Emotion Recognition
-
Authors: Jie Wei, Guanyu Hu, Xinyu Yang, Luu Anh Tuan, Yizhuo Dong
git clone https://github.com/Janie1996/AV4SER.git
You can create an anaconda environment with:
conda env create -f environment.yaml
conda activate AV4SER
a. Download dataset from google-drive. Unzip it and put them under ./DATA/
b. Download model checkpoint from google-drive. Unzip it and put them under ./Checkpoint/
-
Run MDSCM only
python AudioExperiment/evaluation.py
-
Run AVDAL only
python DomainExperiment/evaluation.py
-
Run proposed
python FusionExperiment/SER.py
Coming soon ...
If you have questions, feel free to contact weijie_xjtu@stu.xjtu.edu.cn