@article{speakervid5malargescalehighqualitydatase,
  title = {SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation},
  author = {Youliang Zhang and Zhaoyang Li and Duomin Wang and Jiahe Zhang and Deyu Zhou and Zixin Yin and Xili Dai and Gang Yu and Xiu Li},
  year = {2025},
  eprint = {2507.09862},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.09862},
}