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]

Abstract

Abstract is missing.