Abstract—Major researches in the field of audio classification have neglected the importance of preprocessing step of environmental sound recognition, or using usually classic sound classifiers. The originality of this paper is to construct a complete three modules process, acting dependently, with well defined functions. New method of acoustic sources separation are offered by our process, as well as, a sophisticated framework of binary classifiers is used to promote environmental sound classification. The results show that the proposed system has achieved accuracy higher than 90% for audio concept identification.

Index Terms—Component; concept, audio, encapsulation, classification.

The authors are with REGIM: Research Group on Intelligent Machines University of Sfax, ENIS, BP1173 - 3038, Sfax, Tunisia (e-mail:feki_issam@ieee.org, anis.benammar@ieee.org, adel.alimi@ieee.org).

Cite: Issam Feki, Anis Ben Ammar, and Adel. M. Alimi, "NEW Process to Identify Audio Concepts Based on Binary Classifiers Encapsulation," International Journal of Computer and Electrical Engineering vol. 4, no. 4, pp. 515-518, 2012.