摘要：
Audio Generation with Multiple Conditional Diffusion Model 来源： http://export.arxiv.org/abs/2308.11940 https://conditionaudiogen.github.io/conditionaud 阅读全文
摘要：
VarietySound: Timbre-Controllable Video to Sound Generation via Unsupervised Information Disentanglement 来源： https://doi.org/10.48550/arXiv.2211.10666 阅读全文