@article{clapsepleveragingcontrastivepretrained,
  title = {CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction},
  author = {Hao Ma and Zhiyuan Peng and Xu Li and Mingjie Shao and Xixin Wu and Ju Liu},
  year = {2024},
  eprint = {2402.17455},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.17455v5},
}