ePrints

Performance improvement in single-channel blind separation with pseudo-stereo mixture using cochleagram representation based masks

Lookup NU author(s): Yadi Yuan, Naruephorn Tengtrairat, Dr Wai Lok Woo, Emeritus Professor Satnam Dlay

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

A novel single-channel blind source separation (SCBSS) algorithm using Cochleagram-mask based technique is presented in this paper. The proposed system offers benefits such as resemblance of a stereo signal concept given by one microphone, independent of initialization and a priori knowledge of the sources, improved performance with sources which do not strictly satisfy the windowed-disjoint orthogonality (WDO) condition and reduced computational complexity without the need for iterative optimizations. The separation process comprises three steps: 1) estimation of source characteristics, where the source signals are modelled by the autoregressive process and 2) construction of masks using only the single-channel mixture 3) binary TF masks modification through cochleagram processing 4) improve separation depth through independent component analysis (ICA). Experiment results revealed at least 3dB signal to interference ratio comparing to previous systems [1].

Publication metadata

Author(s): Yuan Y, Tengtrairat N, Woo WL, Dlay SS

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: 2nd IET International Conference on Intelligent Signal Processing 2015 (ISP)

Year of Conference: 2015

Online publication date: 17/11/2016

Acceptance date: 01/01/1900

Publisher: Institution of Engineering and Technology

URL: http://doi.org/10.1049/cp.2015.1790

DOI: 10.1049/cp.2015.1790

Share