The offical PyTorch code for paper "Speech Emotion Recognition Based on Secondary Feature Reconstruction", ICCIA 2021.
numpy>=1.7.1
six>=1.1.0
PyTorch > 0.3
flask >= 1.1.1
Numpy
h5py
nltk
yaml
Step 1. 读data文件夹下的readme。
Step 2. 读取ExtractImage下的readme,并执行。
Step 3. 读取DataArgument下的readme,按步骤执行。
Step 4. 运行Train下的文件,运行多个模型生成不同的概率json。
Step 5. 运行Ensemble下的文件,进行模型集成,得到最后的提交文件。
If you feel this code helpful or use this code or dataset, please cite it as
Z. Yuan, S. Li, W. Zhang, R. Du, X. Sun and H. Wang, "Speech Emotion Recognition Based on Secondary Feature Reconstruction," 2021 6th International Conference on Computational Intelligence and Applications (ICCIA), 2021, pp. 149-154, doi: 10.1109/ICCIA52886.2021.00036.