Towards Musical Data Classification via Wavelet Analysis

  • Authors:
  • Alicja Wieczorkowska

  • Affiliations:
  • -

  • Venue:
  • ISMIS '00 Proceedings of the 12th International Symposium on Foundations of Intelligent Systems
  • Year:
  • 2000

Quantified Score

Hi-index 0.01

Visualization

Abstract

In order to search through a sound database, information about the musical contents has to be attached to the file, otherwise the user has to look for the specific musical information by himself. Wavelet analysis is one of possible tools that can be used as a basis for automatic classification of musical data. In this paper, the author presents wavelet-based parameters extracted from sounds of musical instruments. These parameters have been used as a basis of automatic classification of musical instrument sounds. Tests evaluating the efficiency of such parameterization were performed by means of rough set based algorithms and decision trees. Results of these tests are presented in this paper.