VarietySound: Timbre-Controllable Video to Sound Generation Via Unsupervised Information Disentanglement

Chenye Cui, Zhou Zhao, Yi Ren 0006, Jinglin Liu, Rongjie Huang, Feiyang Chen, Zhefeng Wang, Baoxing Huai, Fei Wu. VarietySound: Timbre-Controllable Video to Sound Generation Via Unsupervised Information Disentanglement. In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023. pages 1-5, IEEE, 2023. [doi]

@inproceedings{CuiZRLHCWHW23,
  title = {VarietySound: Timbre-Controllable Video to Sound Generation Via Unsupervised Information Disentanglement},
  author = {Chenye Cui and Zhou Zhao and Yi Ren 0006 and Jinglin Liu and Rongjie Huang and Feiyang Chen and Zhefeng Wang and Baoxing Huai and Fei Wu},
  year = {2023},
  doi = {10.1109/ICASSP49357.2023.10096353},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10096353},
  researchr = {https://researchr.org/publication/CuiZRLHCWHW23},
  cites = {0},
  citedby = {0},
  pages = {1-5},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023},
  publisher = {IEEE},
  isbn = {978-1-7281-6327-7},
}