DiffRoll: Diffusion-based Generative Music Transcription with Unsupervised Pretraining Capability.
Kin Wai CheukRyosuke SawataToshimitsu UesakaNaoki MurataNaoya TakahashiShusuke TakahashiDorien HerremansYuki MitsufujiPublished in: CoRR (2022)
Keyphrases
- unsupervised learning
- data driven
- generative model
- supervised learning
- anisotropic diffusion
- semi supervised
- unsupervised manner
- music information retrieval
- machine learning
- diffusion process
- semi supervised learning
- image processing
- music retrieval
- computer music
- probabilistic model
- active learning
- object recognition
- multiscale
- bayesian networks
- data sets
- diffusion model
- semisupervised learning
- music scores