Music genre classification based on MPEG-7 audio features

  • Authors:

  • Song Li;Haifeng Li;Lin Ma

  • Affiliations:

  • Harbin Institute of Technology, Harbin, China;Harbin Institute of Technology, Harbin, China;Harbin Institute of Technology, Harbin, China

  • Venue:
  • ICIMCS '10 Proceedings of the Second International Conference on Internet Multimedia Computing and Service
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Music genre is a useful tool which can categorize large music database. MPEG-7 is an international standard for managing audiovisual contents. MPEG-7 audio features are used for audio classification, music instrument classification and speech recognition. In this paper, we present a series of experiments to evaluate the MPEG-7 audio features for music genre classification performance. For the feature extraction, we choose Mel-scale Frequency Cepstrum Coefficients (MFCC), Audio Spectrum Envelop (ASE), Audio Spectrum Projection (ASP) and the combination of Audio Spectrum Centroid, Spread and Flatness. Some comparable results are derived from our database consisting of 7 different genres of music with Gaussian Mixture Model (GMM) classifier.