Chapter

Pattern Recognition

Volume 7914 of the series Lecture Notes in Computer Science pp 254-263

Music Genre Classification: A Semi-supervised Approach

  • Soujanya PoriaAffiliated withComputer Science and Engineering Department, Jadavpur University
  • , Alexander GelbukhAffiliated withCIC, Instituto Politécnico Nacional
  • , Amir HussainAffiliated withDept. of Computing Science and Mathematics, University of Stirling
  • , Sivaji BandyopadhyayAffiliated withComputer Science and Engineering Department, Jadavpur University
  • , Newton HowardAffiliated withBrain Science Foundation

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Music genres can be seen as categorical descriptions used to classify music basing on various characteristics such as instrumentation, pitch, rhythmic structure, and harmonic contents. Automatic music genre classification is important for music retrieval in large music collections on the web. We build a classifier that learns from very few labeled examples plus a large quantity of unlabeled data, and show that our methodology outperforms existing supervised and unsupervised approaches. We also identify salient features useful for music genre classification. We achieve 97.1% accuracy of 10-way classification on real-world audio collections.