@article{drcapdecodingclaplatentswithretrieval,
  title = {DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioning},
  author = {Xiquan Li and Wenxi Chen and Ziyang Ma and Xuenan Xu and Yuzhe Liang and Zhisheng Zheng and Qiuqiang Kong and Xie Chen},
  year = {2024},
  eprint = {2410.09472},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.09472v2},
}