On the Modeling of Musical Solos as Complex Networks

TL;DR

This paper models musical solos as complex networks to analyze their structure, providing a framework that can enhance applications like music classification, generation, and e-learning.

Contribution

It introduces a novel network-based framework for representing melodies and analyzes guitar solos to demonstrate its potential for various music-related applications.

Findings

Network metrics characterize musical pieces effectively

The model can distinguish different guitar styles

Potential applications in music classification and generation

Abstract

Notes in a musical piece are building blocks employed in non-random ways to create melodies. It is the "interaction" among a limited amount of notes that allows constructing the variety of musical compositions that have been written in centuries and within different cultures. Networks are a modeling tool that is commonly employed to represent a set of entities interacting in some way. Thus, notes composing a melody can be seen as nodes of a network that are connected whenever these are played in sequence. The outcome of such a process results in a directed graph. By using complex network theory, some main metrics of musical graphs can be measured, which characterize the related musical pieces. In this paper, we define a framework to represent melodies as networks. Then, we provide an analysis on a set of guitar solos performed by main musicians. Results of this study indicate that the presented model can have an impact on audio and multimedia applications such as music classification, identification, e-learning, automatic music generation, multimedia entertainment.