Diffroll: Diffusion-Based Generative Music Transcription with Unsupervised Pretraining Capability.
Kin Wai CheukRyosuke SawataToshimitsu UesakaNaoki MurataNaoya TakahashiShusuke TakahashiDorien HerremansYuki MitsufujiPublished in: ICASSP (2023)
Keyphrases
- unsupervised learning
- diffusion process
- data driven
- generative model
- semi supervised
- supervised learning
- anisotropic diffusion
- diffusion processes
- audio signals
- diffusion model
- music information retrieval
- computer music
- semisupervised learning
- music score
- discriminative methods
- probabilistic topic models
- music composition
- information diffusion
- music retrieval
- unsupervised manner
- data sets
- topic modeling
- supervised classification
- microarray
- active learning
- machine learning