Discriminative Layered Nonnegative Matrix Factorization for Speech Separation

Files

No files are attached to this item.

View at the publisher (DOI) ›

Date

2016-01-01

Journal Title

17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES

Volume, issue and pages

pp. 560–564

ISSN

2308-457X

Language

English

Abstract

This paper proposes a discriminative layered nonnegative matrix factorization (DL-NMF) for monaural speech separation. The standard NMF conducts the parts-based representation using a single-layer of bases which was recently upgraded to the layered NMF (L-NMF) where a tree of bases was estimated for multi-level or multi-aspect decomposition of a complex mixed signal. In this study, we develop the DL-NMF by extending the generative bases in L-NMF to the discriminative bases which are estimated according to a discriminative criterion. The discriminative criterion is conducted by optimizing the recovery of the mixed spectra from the separated spectra and minimizing the reconstruction errors between separated spectra and original source spectra. The experiments on single-channel speech separation show the superiority of DL-NMF to NMF and L-NMF in terms of the SDR, SIR and SAR measures.

Collections

Conferences Paper
Full item page Statistics

Cite this item

Hsu, C.-C., Chi, T.-S., & Chien, J.-T. (2016). Discriminative Layered Nonnegative Matrix Factorization for Speech Separation. 17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 560–564. https://doi.org/10.21437/Interspeech.2016-415

BibTeX RIS

Citation generated in APA 7th edition style; please check it before use.

Share

Permanent link: https://ir.lib.nycu.edu.tw/handle/11536/146771