HiddenSinger: High-Quality Singing Voice Synthesis via Neural Audio Codec and Latent Diffusion Models.
Ji-Sang HwangSang-Hoon LeeSeong-Whan LeePublished in: CoRR (2023)
Keyphrases
- diffusion models
- high quality
- music information retrieval
- diffusion model
- audio features
- emotion recognition
- information diffusion
- social networks
- text to speech
- audio visual
- acoustic features
- video coding
- influence maximization
- viral marketing
- visual information
- image quality
- motion compensation
- greedy algorithm
- diffusion process
- high resolution
- website
- image processing
- computer vision