24 December 2013 Automatic music genres classification as a pattern recognition problem
Author Affiliations +
Proceedings Volume 9067, Sixth International Conference on Machine Vision (ICMV 2013); 90672A (2013) https://doi.org/10.1117/12.2051595
Event: Sixth International Conference on Machine Vision (ICMV 13), 2013, London, United Kingdom
Abstract
Music genres are the simplest and effect descriptors for searching music libraries stores or catalogues. The paper compares the results of two automatic music genres classification systems implemented by using two different yet simple classifiers (K-Nearest Neighbor and Naïve Bayes). First a 10-12 second sample is selected and features are extracted from it, and then based on those features results of both classifiers are represented in the form of accuracy table and confusion matrix. An experiment carried out on test 60 taken from middle of a song represents the true essence of its genre as compared to the samples taken from beginning and ending of a song. The novel techniques have achieved an accuracy of 91% and 78% by using Naïve Bayes and KNN classifiers respectively.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ihtisham Ul Haq, Ihtisham Ul Haq, Fauzia Khan, Fauzia Khan, Sana Sharif, Sana Sharif, Arsalan Shaukat, Arsalan Shaukat, } "Automatic music genres classification as a pattern recognition problem", Proc. SPIE 9067, Sixth International Conference on Machine Vision (ICMV 2013), 90672A (24 December 2013); doi: 10.1117/12.2051595; https://doi.org/10.1117/12.2051595
PROCEEDINGS
6 PAGES


SHARE
Back to Top