@inproceedings{matsuo2021self-augmented,
  title={Self-Augmented Multi-Modal Feature Embedding},
  author={Matsuo, Shinnosuke and Iwana, Brian Kenji and Uchida, Seiichi},
  booktitle={International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
  pages={3995--3999},
  year={2021},
  doi={10.1109/icassp39728.2021.9413974 },
}