Papers
arxiv:2210.05148

DiffRoll: Diffusion-based Generative Music Transcription with Unsupervised Pretraining Capability

Published on Oct 11, 2022
Authors:
,
,
,
,
,
,

Abstract

A novel generative approach, DiffRoll, treats automatic music transcription as a conditional task, outperforming discriminative methods and capable of transcription, generation, and inpainting music without classifiers.

AI-generated summary

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. Source code and demonstration are available https://sony.github.io/DiffRoll/.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2210.05148 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2210.05148 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2210.05148 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.