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

  • Authors
  • Slizovskaia, O.; Kim L.; Haro G.; Gómez E.
  • UPF authors
  • HARO ORTEGA, GLORIA;
  • Type
  • Scholarly articles
  • Journal títle
  • IEEE International Conference on Acoustics, Speech, and Signal Processing
  • Publication year
  • 2019
  • Pages
  • 0-0
  • ISSN
  • 1520-6149
  • Publication State
  • Published
  • Abstract
  • Can we perform an end-to-end sound source separation (SSS) with a variable number of sources using a deep learning model? This paper presents 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 can be further extended to other types of conditioning such as audio-visual SSS and score-informed SSS.
  • Complete citation
  • Slizovskaia, O.; Kim L.; Haro G.; Gómez E.. End-to-End Sound Source Separation Conditioned On Instrument Labels. IEEE International Conference on Acoustics, Speech, and Signal Processing 2019; ( ).