Abstract

Monaural source separation is useful for many real-world applications though it is a challenging problem. In this paper, we study deep learning for monaural speech separation. We propose the joint optimization of the deep learning models (deep neural networks and recurrent neural networks) with an extra masking layer, which enforces a reconstruction constraint. Moreover, we explore a discriminative training criterion for the neural networks to further enhance the separation performance. We evaluate our approaches using the TIMIT speech corpus for a monaural speech separation task. Our proposed models achieve about 3.8∼4.9 dB SIR gain compared to NMF models, while maintaining better SDRs and SARs.

Original languageEnglish (US)
Title of host publication2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1562-1566
Number of pages5
ISBN (Print)9781479928927
DOIs
StatePublished - 2014
Event2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 - Florence, Italy
Duration: May 4 2014May 9 2014

Publication series

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

Other

Other2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
Country/TerritoryItaly
CityFlorence
Period5/4/145/9/14

Keywords

  • Deep Learning
  • Monaural Source Separation
  • Time-Frequency Masking

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Deep learning for monaural speech separation'. Together they form a unique fingerprint.

Cite this