@misc{wu2022large,
  title={Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation},
  author={Yusong Wu and Ke Chen and Tianyu Zhang and Yuchen Hui and Taylor Berg-Kirkpatrick and Shlomo Dubnov},
  year={2022},
  eprint={2211.06687},
  archivePrefix={arXiv},
  primaryClass={cs.SD},
  url={https://arxiv.org/abs/2211.06687}
}