Source separation using dictionary learning and deep recurrent neural network with locality preserving constraint

Tuan Pham, Yuan Shan Lee, Seksan Mathulaprangsan, Jia Ching Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Deep learning is a popular method for monaural source separation, and especially for extracting a singing voice from a single-channel song. However, deep learning-based source separation ignores the geometrical structure of the input data. This work develops a novel approach to source separation that is based on non-negative matrix factorization (NMF) and deep recurrent neural networks (DRNN) with a locality-preserving constraint. First, NMF was used to learn patterns from training data. The learned patterns are linearly combined with the output of DRNN. Second, a locality-preserving constraint is developed to exploit the inner-structure of the input data in the DRNN learning process. Experimental results obtained using the MIR-1K dataset reveal that the proposed algorithm outperforms the baselines.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Multimedia and Expo, ICME 2017
PublisherIEEE Computer Society
Pages151-156
Number of pages6
ISBN (Electronic)9781509060672
DOIs
StatePublished - 28 Aug 2017
Event2017 IEEE International Conference on Multimedia and Expo, ICME 2017 - Hong Kong, Hong Kong
Duration: 10 Jul 201714 Jul 2017

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2017 IEEE International Conference on Multimedia and Expo, ICME 2017
Country/TerritoryHong Kong
CityHong Kong
Period10/07/1714/07/17

Keywords

  • Deep recurrent neural network
  • Locality preserving constraint
  • Nonnegative matrix factorization

Fingerprint

Dive into the research topics of 'Source separation using dictionary learning and deep recurrent neural network with locality preserving constraint'. Together they form a unique fingerprint.

Cite this