Blind Source Separation for a Robust Audio Recognition Scheme in Multiple Sound-Sources Environment

DOI

10.2991/meic-15.2015.358How to use a DOI?

Keywords

audio recognition; audio fingerprinting; multiple sound-sources environment; blind source separation

Abstract

In multiple sound-sources environment, robustness is a major challenge for audio recognition system based on audio fingerprinting, because mixed audio signals may make recognition rate has a significant decline. This paper proposes a novel audio fingerprinting method, which uses blind source separation to divide mixed audio signals into independent components and each is close to its original sound-source, then the classical Philips scheme can perform accurately identifying. Experimental results show that novel scheme is quite robust in noisy conditions where uncertain audio signals mixed by various numbers of sound-source, even though the feature of each original sound-source and their mixed model are unknown.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Wei Han
AU  - Songbin Zhou
AU  - Chang Li
AU  - Yisen Liu
AU  - Zhe Liu
PY  - 2015/04
DA  - 2015/04
TI  - Blind Source Separation for a Robust Audio Recognition Scheme in Multiple Sound-Sources Environment
BT  - Proceedings of the 2015 International Conference on Mechatronics, Electronic, Industrial and Control Engineering
PB  - Atlantis Press
SP  - 1564
EP  - 1568
SN  - 2352-5401
UR  - https://doi.org/10.2991/meic-15.2015.358
DO  - 10.2991/meic-15.2015.358
ID  - Han2015/04
ER  -