A Comparative Study on Content-Based Music Genre Classification

Tao Li, Mitsunori Ogihara, Qi Li

Research output: Contribution to journalArticle

259 Citations (Scopus)

Abstract

Content-based music genre classification is a fundamental component of music information retrieval systems and has been gaining importance and enjoying a growing amount of attention with the emergence of digital music on the Internet. Currently little work has been done on automatic music genre classification, and in addition, the reported classification accuracies are relatively low. This paper proposes a new feature extraction method for music genre classification, DWCHs 1. DWCHs capture the local and global information of music signals simultaneously by computing histograms on their Daubechies wavelet coefficients. Effectiveness of this new feature and of previously studied features are compared using various machine learning classification algorithms, including Support Vector Machines and Linear Discriminant Analysis. It is demonstrated that the use of DWCHs significantly improves the accuracy of music genre classification.

Original languageEnglish (US)
Pages (from-to)282-289
Number of pages8
JournalSIGIR Forum (ACM Special Interest Group on Information Retrieval)
Issue numberSPEC. ISS.
StatePublished - 2003
Externally publishedYes

Fingerprint

Computer music
Information retrieval systems
Discriminant analysis
Support vector machines
Learning systems
Music
Comparative study
Feature extraction
Internet
Support vector machine
Coefficients
World Wide Web
Wavelets
Information retrieval
Digital music
Machine learning

Keywords

  • Feature extraction
  • Multi-class classification
  • Music Genre Classification
  • Wavelet coefficients histogram

ASJC Scopus subject areas

  • Hardware and Architecture
  • Management Information Systems

Cite this

A Comparative Study on Content-Based Music Genre Classification. / Li, Tao; Ogihara, Mitsunori; Li, Qi.

In: SIGIR Forum (ACM Special Interest Group on Information Retrieval), No. SPEC. ISS., 2003, p. 282-289.

Research output: Contribution to journalArticle

@article{2f955975a5f845969b1810a1a27ce9bc,
title = "A Comparative Study on Content-Based Music Genre Classification",
abstract = "Content-based music genre classification is a fundamental component of music information retrieval systems and has been gaining importance and enjoying a growing amount of attention with the emergence of digital music on the Internet. Currently little work has been done on automatic music genre classification, and in addition, the reported classification accuracies are relatively low. This paper proposes a new feature extraction method for music genre classification, DWCHs 1. DWCHs capture the local and global information of music signals simultaneously by computing histograms on their Daubechies wavelet coefficients. Effectiveness of this new feature and of previously studied features are compared using various machine learning classification algorithms, including Support Vector Machines and Linear Discriminant Analysis. It is demonstrated that the use of DWCHs significantly improves the accuracy of music genre classification.",
keywords = "Feature extraction, Multi-class classification, Music Genre Classification, Wavelet coefficients histogram",
author = "Tao Li and Mitsunori Ogihara and Qi Li",
year = "2003",
language = "English (US)",
pages = "282--289",
journal = "SIGIR Forum (ACM Special Interest Group on Information Retrieval)",
issn = "0163-5840",
publisher = "Association for Computing Machinery (ACM)",
number = "SPEC. ISS.",

}

TY - JOUR

T1 - A Comparative Study on Content-Based Music Genre Classification

AU - Li, Tao

AU - Ogihara, Mitsunori

AU - Li, Qi

PY - 2003

Y1 - 2003

N2 - Content-based music genre classification is a fundamental component of music information retrieval systems and has been gaining importance and enjoying a growing amount of attention with the emergence of digital music on the Internet. Currently little work has been done on automatic music genre classification, and in addition, the reported classification accuracies are relatively low. This paper proposes a new feature extraction method for music genre classification, DWCHs 1. DWCHs capture the local and global information of music signals simultaneously by computing histograms on their Daubechies wavelet coefficients. Effectiveness of this new feature and of previously studied features are compared using various machine learning classification algorithms, including Support Vector Machines and Linear Discriminant Analysis. It is demonstrated that the use of DWCHs significantly improves the accuracy of music genre classification.

AB - Content-based music genre classification is a fundamental component of music information retrieval systems and has been gaining importance and enjoying a growing amount of attention with the emergence of digital music on the Internet. Currently little work has been done on automatic music genre classification, and in addition, the reported classification accuracies are relatively low. This paper proposes a new feature extraction method for music genre classification, DWCHs 1. DWCHs capture the local and global information of music signals simultaneously by computing histograms on their Daubechies wavelet coefficients. Effectiveness of this new feature and of previously studied features are compared using various machine learning classification algorithms, including Support Vector Machines and Linear Discriminant Analysis. It is demonstrated that the use of DWCHs significantly improves the accuracy of music genre classification.

KW - Feature extraction

KW - Multi-class classification

KW - Music Genre Classification

KW - Wavelet coefficients histogram

UR - http://www.scopus.com/inward/record.url?scp=1542439119&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542439119&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:1542439119

SP - 282

EP - 289

JO - SIGIR Forum (ACM Special Interest Group on Information Retrieval)

JF - SIGIR Forum (ACM Special Interest Group on Information Retrieval)

SN - 0163-5840

IS - SPEC. ISS.

ER -