Exploiting Nonnegative Matrix Factorization with Mixed Group Sparsity Constraint to Separate Speech Signal from Single-channel Mixture with Unknown Ambient Noise

Duong, Thanh Thi Hien and Nguyen, Phuong Cong and Nguyen, Cuong Quoc (2018) Exploiting Nonnegative Matrix Factorization with Mixed Group Sparsity Constraint to Separate Speech Signal from Single-channel Mixture with Unknown Ambient Noise. EAI Endorsed Transactions on Context-aware Systems and Applications, 4 (13): e5. ISSN 2409-0026

[img]
Preview
Text
eai.14-3-2018.154342.pdf - Published Version
Available under License Creative Commons Attribution No Derivatives.

Download (745kB) | Preview

Abstract

This paper focuses on solving a challenging speech enhancement problem: improving the desired speech from a single-channel audio signal containing high-level unspecified noise (possibly environmental noise, music, other sounds, etc.). Using source separation technique, we investigate a solution combining nonnegative matrix factorization (NMF) with mixed group sparsity constraint that allows exploiting generic noise spectral model to guide the separation process. The experiment performed on a set of benchmarked audio signals with different types of real-world noise shows that the proposed algorithm yields better quantitative results in term of the signal-to-distortion ratio than the previously published algorithms.

Item Type: Article
Uncontrolled Keywords: Speech enhancement, source separation, nonnegative matrix factorizarion (NMF), sparsity constraint, generic source spectral model
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
QA75 Electronic computers. Computer science
Depositing User: EAI Editor II.
Date Deposited: 16 Sep 2020 08:38
Last Modified: 16 Sep 2020 08:38
URI: https://eprints.eudl.eu/id/eprint/313

Actions (login required)

View Item View Item