English

End-to-End Sound Source Separation Conditioned On Instrument Labels

Sound 2019-05-10 v2 Machine Learning Audio and Speech Processing

Abstract

Can we perform an end-to-end music source separation with a variable number of sources using a deep learning model? We present an extension of the Wave-U-Net model which allows end-to-end monaural source separation with a non-fixed number of sources. Furthermore, we propose multiplicative conditioning with instrument labels at the bottleneck of the Wave-U-Net and show its effect on the separation results. This approach leads to other types of conditioning such as audio-visual source separation and score-informed source separation.

Keywords

Cite

@article{arxiv.1811.01850,
  title  = {End-to-End Sound Source Separation Conditioned On Instrument Labels},
  author = {Olga Slizovskaia and Leo Kim and Gloria Haro and Emilia Gomez},
  journal= {arXiv preprint arXiv:1811.01850},
  year   = {2019}
}

Comments

5 pages, 2 figures, 2 tables, ICASSP 2019

R2 v1 2026-06-23T05:04:43.300Z