English

Bespoke Neural Networks for Score-Informed Source Separation

Sound 2020-09-30 v1 Machine Learning Audio and Speech Processing

Abstract

In this paper, we introduce a simple method that can separate arbitrary musical instruments from an audio mixture. Given an unaligned MIDI transcription for a target instrument from an input mixture, we synthesize new mixtures from the midi transcription that sound similar to the mixture to be separated. This lets us create a labeled training set to train a network on the specific bespoke task. When this model applied to the original mixture, we demonstrate that this method can: 1) successfully separate out the desired instrument with access to only unaligned MIDI, 2) separate arbitrary instruments, and 3) get results in a fraction of the time of existing methods. We encourage readers to listen to the demos posted here: https://git.io/JUu5q.

Keywords

Cite

@article{arxiv.2009.13729,
  title  = {Bespoke Neural Networks for Score-Informed Source Separation},
  author = {Ethan Manilow and Bryan Pardo},
  journal= {arXiv preprint arXiv:2009.13729},
  year   = {2020}
}

Comments

ISMIR 2020 - Late Breaking Demo

R2 v1 2026-06-23T18:51:57.185Z