Diffsinger Extension

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism

493G Final Project

DiffSinger, an acoustic model for SVS based on the diffusion probabilistic model.

• Diffsinger Week 2 Update
• Diffsinger Week 1 Update

TODO:

• Deploy locally
• Know more about standard Diffusion model

Related Links:

• Repository: https://github.com/MoonInTheRiver/DiffSinger
• Paper:  https://arxiv.org/abs/2105.02446
• Demo: https://aistudio.baidu.com/projectdetail/4596296