A Proposed System for Sound Retrieval Using MAS and ANN

Abstract

As the use of sounds for computer interfaces, electronic equipment andmultimedia contents, has increased, the role of sound design tools has becomemore important. In sound retrieval, picking one sound out from huge data istroublesome for users because of the difficulty of simultaneously listening to pluralsounds and sometimes there are difficulties with speech and sound recognition.Consequently, an efficient retrieval method is required for sound databases.This research proposes a system aim to deal with sound retrieval in both twocases: authenticity and normal. In the first case, authenticity, two algorithms hasbeen develop one for building the authentication database and the second deal withuser sound sample to retrieve the matched authenticated samples. In the secondcase normal we develop algorithm to deal with user sound sample to retrieve all thematched samples. Many techniques used in this proposed system such as ArtificialNeural Network (ANN), Data Encryption Standard (DES), Multi Agent System(MAS) and Fourier transformation (FT). Using these combinations of advancedand adaptive techniques supports the system to be reliable, secure and parallel.