Discriminative deep recurrent neural networks for monaural speech separation

Guan Xiang Wang, Chung Chien Hsu, Jen-Tzung Chien

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

20 Scopus citations

Abstract

Deep neural network is now a new trend towards solving different problems in speech processing. In this paper, we propose a discriminative deep recurrent neural network (DRNN) model for monaural speech separation. Our idea is to construct DRNN as a regression model to discover the deep structure and regularity for signal reconstruction from a mixture of two source spectra. To reinforce the discrimination capability between two separated spectra, we estimate DRNN separation parameters by minimizing an integrated objective function which consists of two measurements. One is the within-source reconstruction errors due to the individual source spectra while the other conveys the discrimination information which preserves the mutual difference between two source spectra during the supervised training procedure. This discrimination information acts as a kind of regularization so as to maintain between-source separation in monaural source separation. In the experiments, we demonstrate the effectiveness of the proposed method for speech separation compared with the other methods.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2544-2548
Number of pages5
ISBN (Electronic)9781479999880
DOIs
StatePublished - 18 May 2016
Event41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China
Duration: 20 Mar 201625 Mar 2016

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2016-May
ISSN (Print)1520-6149

Conference

Conference41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
CountryChina
CityShanghai
Period20/03/1625/03/16

Keywords

  • deep learning
  • discriminative learning
  • monaural speech separation
  • neural network

Fingerprint Dive into the research topics of 'Discriminative deep recurrent neural networks for monaural speech separation'. Together they form a unique fingerprint.

Cite this