MAID: A Conditional Diffusion Model for Long Music Audio Inpainting.
Kaiyang LiuWendong GanChenchen YuanPublished in: ICASSP (2023)
Keyphrases
- diffusion model
- audio signals
- music score
- music information retrieval
- music scores
- audio features
- diffusion models
- audio content
- music retrieval
- audio signal
- music genre classification
- audio recordings
- audio files
- speech music discrimination
- anisotropic diffusion
- music collections
- automatic music genre classification
- information diffusion
- diffusion process
- polyphonic music
- content based music retrieval
- musical instruments
- audio visual
- diffusion tensor
- texture synthesis
- denoising
- motion estimation
- image analysis
- multiscale
- image sequences
- image processing
- decision making