DiffRoll - Music Transcription with Diffusion
Great work Cheuk Kin Wai on his latest paper on DiffRoll: Diffusion-based Generative Music Transcription with Unsupervised Pretraining Capability
Cheuk, K. W., Sawata, R., Uesaka, T., Murata, N., Takahashi, N., Takahashi, S., ... & Mitsufuji, Y. (2022). DiffRoll: Diffusion-based Generative Music Transcription with Unsupervised Pretraining Capability. arXiv preprint arXiv:2210.05148.
Demo & Source code available here.
Abstract:
In this paper we propose a novel generative approach, DiffRoll, to tackle automatic music transcription (AMT). Instead of treating AMT as a discriminative task in which the model is trained to convert spectrograms into piano rolls, we think of it as a conditional generative task where we train our model to generate realistic looking piano rolls from pure Gaussian noise conditioned on spectrograms. This new AMT formulation enables DiffRoll to transcribe, generate and even inpaint music. Due to the classifier-free nature, DiffRoll is also able to be trained on unpaired datasets where only piano rolls are available. Our experiments show that DiffRoll outperforms its discriminative counterpart by 19 percentage points (ppt.) and our ablation studies also indicate that it outperforms similar existing methods by 4.8 ppt.