Instrument Separation of Symbolic Music by Explicitly Guided Diffusion Model
Sound
2022-09-08 v1 Multimedia
Audio and Speech Processing
Abstract
Similar to colorization in computer vision, instrument separation is to assign instrument labels (e.g. piano, guitar...) to notes from unlabeled mixtures which contain only performance information. To address the problem, we adopt diffusion models and explicitly guide them to preserve consistency between mixtures and music. The quantitative results show that our proposed model can generate high-fidelity samples for multitrack symbolic music with creativity.
Keywords
Cite
@article{arxiv.2209.02696,
title = {Instrument Separation of Symbolic Music by Explicitly Guided Diffusion Model},
author = {Sangjun Han and Hyeongrae Ihm and DaeHan Ahn and Woohyung Lim},
journal= {arXiv preprint arXiv:2209.02696},
year = {2022}
}
Comments
Submitted to NeurIPS 2022 Workshop on Machine Learning for Creativity and Design