Exploiting Nonnegative Matrix Factorization with Mixed Group Sparsity Constraint to Separate Speech Signal from Single-channel Mixture with Unknown Ambient Noise
Journal Title: EAI Endorsed Transactions on Context-aware Systems and Applications - Year 2017, Vol 4, Issue 13
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.
Authors and Affiliations
Thanh Thi Hien Duong, Phuong Cong Nguyen, Cuong Quoc Nguye
Keywords
Related Articles
- EP ID EP45802
- DOI http://dx.doi.org/10.4108/eai.14-3-2018.154342
- Views 240
- Downloads 0
Maintenance process control: cellular automata approach
In this work we consider an industrial maintenance process control problem using cellular automata approach. The problem consists on finding an optimal control for the assignment and the displacement of agents in a spati...
Context-aware Readings with Inbooki
E-books are more and more spreading among readers, who take advantage from the capability of reading them on different devices and of storing a whole library of books in a light and portable device. What is still missing...
Improving Control Mechanism at Routers in TCP/IP Network
The existing control mechanisms at the network nodes have a good active and very effective at each local router, but they do not still strong enough to control nonlinear and dynamical behaviour of the network. Therefore,...
Assistance to assessing rating students by language tuple- 4 scale
In this paper, we introduce an assistance to assessing rating the annual learning and process training of students in the opinion of experts, the approach of hedge algebra. It is advisary to make optimally fuzzy paramete...
Context-Aware Mobility in Internet of Thing: A Survey
The rapid growth in Internet of Thing (IoT) yields big data that require management, computing, authentication, and analysis. In the first step of IoT, the static things are connected together such as: sensors, cameras,...