Toggle Main Menu Toggle Search

Open Access padlockePrints

Single-channel separation using underdetermined blind autoregressive model and least absolute deviation

Lookup NU author(s): Naruephorn Tengtrairat, Dr Wai Lok Woo

Downloads

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


Abstract

A novel "artificial stereo" mixture is proposed to resemble a synthetic stereo signal for solving the signal-channel blind source separation (SCBSS) problem. The proposed SCBSS framework takes the advantages of the following desirable properties; one microphone; no training phase; no parameter turning; independent of initialization and a priori data of the sources. The artificial stereo mixture is formulated by weighting and time-shifting the single-channel observed mixture. Separability analysis of the proposed mixture model has also been elicited to examine that the artificial stereo mixture is separable. For the separation process, mixing coefficients of sources are estimated where the source signals are modeled by the autoregressive process. Subsequently, a binary time-frequency mask can then be constructed by evaluating the least absolute deviation cost function. Finally, experimental testing on autoregressive sources has shown that the proposed framework yields superior separation performance and is computationally very fast compared with existing SCBSS methods. (C) 2014 Elsevier B.V. All rights reserved.


Publication metadata

Author(s): Tengtrairat N, Woo WL

Publication type: Article

Publication status: Published

Journal: Neurocomputing

Year: 2015

Volume: 147

Pages: 412-425

Print publication date: 05/01/2015

Online publication date: 28/06/2014

Acceptance date: 17/06/2014

ISSN (print): 0925-2312

ISSN (electronic): 1872-8286

Publisher: Elsevier

URL: http://dx.doi.org/10.1016/j.neucom.2014.06.043

DOI: 10.1016/j.neucom.2014.06.043


Altmetrics

Altmetrics provided by Altmetric


Share