/MS-SincResNet

This paper has been accepted in ACM ICMR 2021.

Primary LanguagePython

MS-SincResNet

MS-SincResNet: Joint learning of 1D and 2D kernels using multi-scale SincNet and ResNet for music genre classification

This paper has been accepted in ACM ICMR 2021.

Link: https://dl.acm.org/doi/abs/10.1145/3460426.3463619

Usage:

# You can take main.py as reference for training.
python main.py
# You can take demo.py as reference for demonstration (also can obtain the leared 2D representation by using MS-SincResNet) 
python demo.py

Citation:

@inproceedings{chang2021ms,
  title={MS-SincResNet: Joint learning of 1D and 2D kernels using multi-scale SincNet and ResNet for music genre classification},
  author={Chang, Pei-Chun and Chen, Yong-Sheng and Lee, Chang-Hsing},
  booktitle={Proceedings of the 2021 International Conference on Multimedia Retrieval},
  pages={29--36},
  year={2021}
}