Classification of Turkish makam music: a topological approach

Classification of Turkish makam music: a topological approach

In this paper, we study Turkish makam music, a system of varied melodies and chords, computationally. Our main goal is to classify the makams using their notes. For this reason, we utilize the topology of complex networks. We first represent songs with weighted networks where vertices and edges corr...

Full description

Saved in:
Bibliographic Details
Published in:Journal of mathematics and music (Society for Mathematics and Computation in Music) Vol. 13; no. 2; pp. 135 - 149
Main Authors: Aktas, Mehmet Emin, Akbas, Esra, Papayik, Jason, Kovankaya, Yunus
Format: Journal Article
Language:English
Published: Baton Rouge Taylor & Francis 04-05-2019
Taylor & Francis Ltd
Subjects:
62-07
Algorithms
Apexes
applied computing
Chords (geometry)
Classification
complex networks
diffusion Fréchet function
Graph theory
Machine learning
Music
music classification
music information retrieval
Network topologies
Networks
Turkish makam music
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we study Turkish makam music, a system of varied melodies and chords, computationally. Our main goal is to classify the makams using their notes. For this reason, we utilize the topology of complex networks. We first represent songs with weighted networks where vertices and edges correspond to musical notes and their co-occurrences respectively. We then define the diffusion Fréchet function over the weighted networks to encode the network topology and finally reach our goal by combining the function values with machine-learning algorithms. Our experiments show that such network representation with the diffusion Fréchet function is promising in classifying makam music and more effective than the n-gram technique, which is the most-used automated makam classification method. We believe that our method can be extended to any music, not only makam music.
ISSN:1745-9737
1745-9745
DOI:10.1080/17459737.2019.1622810