@article{multiscalematchingdrivenbycrossmodal,
  title = {Multiscale Matching Driven by Cross-Modal Similarity Consistency for Audio-Text Retrieval},
  author = {Qian Wang and Jia-Chen Gu and Zhen-Hua Ling},
  year = {2024},
  eprint = {2403.10146},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.10146v1},
}