Musical Genres: Beating to the Rhythms of Different Drums

TL;DR

This paper presents a novel rhythm-based approach using complex network analysis and Markov models for automatic music genre classification, demonstrating effective results with statistical and clustering methods.

Contribution

It introduces a new rhythm-based feature extraction method using complex networks and Markov models for improved music genre classification.

Findings

Effective genre classification demonstrated by high Kappa coefficient.

Successful clustering of rhythmic patterns with hierarchical clustering.

Rhythm features outperform traditional methods in accuracy.

Abstract

Online music databases have increased signicantly as a consequence of the rapid growth of the Internet and digital audio, requiring the development of faster and more efficient tools for music content analysis. Musical genres are widely used to organize music collections. In this paper, the problem of automatic music genre classification is addressed by exploring rhythm-based features obtained from a respective complex network representation. A Markov model is build in order to analyse the temporal sequence of rhythmic notation events. Feature analysis is performed by using two multivariate statistical approaches: principal component analysis(unsupervised) and linear discriminant analysis (supervised). Similarly, two classifiers are applied in order to identify the category of rhythms: parametric Bayesian classifier under gaussian hypothesis (supervised), and agglomerative hierarchical clustering (unsupervised). Qualitative results obtained by Kappa coefficient and the obtained clusters corroborated the effectiveness of the proposed method.