@article{tellwhatyouhearfromwhatyouseevideoto,
  title = {Tell What You Hear From What You See -- Video to Audio Generation Through Text},
  author = {Xiulong Liu and Kun Su and Eli Shlizerman},
  year = {2024},
  eprint = {2411.05679},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.05679v3},
}