A style transfer approach to source separation

Shrikant Venkataramani, Efthymios Tzinis, Paris Smaragdis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Training neural networks for source separation involves presenting a mixture recording at the input of the network and updating network parameters in order to produce an output that resembles the clean source. Consequently, supervised source separation depends on the availability of paired mixture-clean training examples. In this paper, we interpret source separation as a style transfer problem. We present a variational auto-encoder network that exploits the commonality across the domain of mixtures and the domain of clean sounds and learns a shared latent representation across the two domains. Using these cycle-consistent variational auto-encoders, we learn a mapping from the mixture domain to the domain of clean sounds and perform source separation without explicitly supervising with paired training examples.

Original languageEnglish (US)
Title of host publication2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages170-174
Number of pages5
ISBN (Electronic)9781728111230
DOIs
StatePublished - Oct 2019
Event2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2019 - New Paltz, United States
Duration: Oct 20 2019Oct 23 2019

Publication series

NameIEEE Workshop on Applications of Signal Processing to Audio and Acoustics
Volume2019-October
ISSN (Print)1931-1168
ISSN (Electronic)1947-1629

Conference

Conference2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2019
Country/TerritoryUnited States
CityNew Paltz
Period10/20/1910/23/19

Keywords

  • Style transfer
  • consistency loss
  • deep learning
  • domain translation
  • neural networks
  • source separation
  • unsupervised learning

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'A style transfer approach to source separation'. Together they form a unique fingerprint.

Cite this