Musical Sound Classification based on Wavelet Analysis

Issue title: Intelligent Systems

Article type: Research Article

Authors: Wieczorkowska, Alicja

Affiliations: Polish-Japanese Institute of Information Technology, ul. Koszykowa 86, 02-008 Warsaw, Poland (e-mail: [email protected]

Abstract: Contents-based searching through audio data is basically restricted to metadata, which are attached manually to the file. Otherwise, users have to look for the specific musical information alone. Nevertheles, when classifiers based on descriptors extracted from sounds analytically are used, automatic classification can be in some cases possible. For instance, wavelet analysis can be used as a basis for automatic classification of audio data. In this paper, classification of musical instrument sounds based on wavelet parameterization is described. Decision trees and rough set based algorithms are used as classification tools. The parameterization is very simple, but the efficiency of classification proves that automatic classification of these sounds is possible.

Keywords: Soft Computing, Knowledge Discovery, Wavelet Analysis, Sound Classification

Journal: Fundamenta Informaticae, vol. 47, no. 1-2, pp. 175-188, 2001