End-To-End Non-Negative Autoencoders for Sound Source Separation

Shrikant Venkataramani, Efthymios Tzinis, Paris Smaragdis

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

Abstract

Discriminative models for source separation have recently been shown to produce impressive results. However, when operating on sources outside of the training set, these models can not perform as well and are cumbersome to update. Classical methods like Nonnegative Matrix Factorization (NMF) provide modular approaches to source separation that can be easily updated to adapt to new mixture scenarios. In this paper, we generalize NMF to develop end-to-end non-negative auto-encoders and demonstrate how they can be used for source separation. Our experiments indicate that these models deliver comparable separation performance to discriminative approaches, while retaining the modularity of NMF and the modeling flexibility of neural networks.

Original languageEnglish (US)
Title of host publication2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages116-120
Number of pages5
ISBN (Electronic)9781509066315
DOIs
StatePublished - May 2020
Externally publishedYes
Event2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Barcelona, Spain
Duration: May 4 2020May 8 2020

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2020-May
ISSN (Print)1520-6149

Conference

Conference2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
Country/TerritorySpain
CityBarcelona
Period5/4/205/8/20

Keywords

  • Non-negative autoencoder
  • deep learning
  • end-to-end
  • non-negative matrix factorization
  • single-channel audio separation
  • source separation

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'End-To-End Non-Negative Autoencoders for Sound Source Separation'. Together they form a unique fingerprint.

Cite this