Proceeding of the past Conferences /

New Music Concepts 2020

Evaluation of Convolutional Neural Network and Four Typical Classification Techniques for Music Genres Classification

Part of the New Music Concepts book series (NMC volume 7)
ISBN: 978-88-944350-3-0

Author(s): Hayder K. Fatlawi, Attila Kiss

Abstract: Classification of Music genres has increasing research interest due to the need of the multimedia websites categorization and user profiling. Music signals require many of preprocessing and features extraction operations. In this report, four typical classifiers have been used with 40 extracted features while CNN utilized to classify images that obtained from waveform and Spectrogram representations of music. The results showed that Random Forest classifier had the best performance with 71% validation accuracy.

Keywords: Music Genres, Convolution Neural Network, Random Forest, Decision Tree, Bayesian model