Music clustering with features from different information sources

Tao Li, Mitsunori Ogihara, Wei Peng, Bo Shao, Shenghuo Zhu

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Efficient and intelligent music information retrieval is a very important topic of the 21st century. With the ultimate goal of building personal music information retrieval systems, this paper studies the problem of identifying similar artists using features from diverse information sources. In this paper, we first present a clustering algorithm that integrates features from both sources to perform bimodal learning. We then present an approach based on the generalized constraint clustering algorithm by incorporating the instance-level constraints. The algorithms are tested on a data set consisting of 570 songs from 53 albums of 41 artists using artist similarity provided by All Music Guide. Experimental results show that the accuracy of artist similarity identification can be significantly improved.

Original languageEnglish (US)
Article number4797802
Pages (from-to)477-484
Number of pages8
JournalIEEE Transactions on Multimedia
Volume11
Issue number3
DOIs
StatePublished - Apr 2009

Fingerprint

Clustering algorithms
Computer music
Information retrieval systems
Information retrieval

Keywords

  • Clustering
  • Different information sources
  • Machine learning
  • Music information retrieval

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Media Technology
  • Computer Science Applications

Cite this

Music clustering with features from different information sources. / Li, Tao; Ogihara, Mitsunori; Peng, Wei; Shao, Bo; Zhu, Shenghuo.

In: IEEE Transactions on Multimedia, Vol. 11, No. 3, 4797802, 04.2009, p. 477-484.

Research output: Contribution to journalArticle

Li, Tao ; Ogihara, Mitsunori ; Peng, Wei ; Shao, Bo ; Zhu, Shenghuo. / Music clustering with features from different information sources. In: IEEE Transactions on Multimedia. 2009 ; Vol. 11, No. 3. pp. 477-484.
@article{48efcb1eb02d4e798f399ae298325891,
title = "Music clustering with features from different information sources",
abstract = "Efficient and intelligent music information retrieval is a very important topic of the 21st century. With the ultimate goal of building personal music information retrieval systems, this paper studies the problem of identifying similar artists using features from diverse information sources. In this paper, we first present a clustering algorithm that integrates features from both sources to perform bimodal learning. We then present an approach based on the generalized constraint clustering algorithm by incorporating the instance-level constraints. The algorithms are tested on a data set consisting of 570 songs from 53 albums of 41 artists using artist similarity provided by All Music Guide. Experimental results show that the accuracy of artist similarity identification can be significantly improved.",
keywords = "Clustering, Different information sources, Machine learning, Music information retrieval",
author = "Tao Li and Mitsunori Ogihara and Wei Peng and Bo Shao and Shenghuo Zhu",
year = "2009",
month = "4",
doi = "10.1109/TMM.2009.2012942",
language = "English (US)",
volume = "11",
pages = "477--484",
journal = "IEEE Transactions on Multimedia",
issn = "1520-9210",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Music clustering with features from different information sources

AU - Li, Tao

AU - Ogihara, Mitsunori

AU - Peng, Wei

AU - Shao, Bo

AU - Zhu, Shenghuo

PY - 2009/4

Y1 - 2009/4

N2 - Efficient and intelligent music information retrieval is a very important topic of the 21st century. With the ultimate goal of building personal music information retrieval systems, this paper studies the problem of identifying similar artists using features from diverse information sources. In this paper, we first present a clustering algorithm that integrates features from both sources to perform bimodal learning. We then present an approach based on the generalized constraint clustering algorithm by incorporating the instance-level constraints. The algorithms are tested on a data set consisting of 570 songs from 53 albums of 41 artists using artist similarity provided by All Music Guide. Experimental results show that the accuracy of artist similarity identification can be significantly improved.

AB - Efficient and intelligent music information retrieval is a very important topic of the 21st century. With the ultimate goal of building personal music information retrieval systems, this paper studies the problem of identifying similar artists using features from diverse information sources. In this paper, we first present a clustering algorithm that integrates features from both sources to perform bimodal learning. We then present an approach based on the generalized constraint clustering algorithm by incorporating the instance-level constraints. The algorithms are tested on a data set consisting of 570 songs from 53 albums of 41 artists using artist similarity provided by All Music Guide. Experimental results show that the accuracy of artist similarity identification can be significantly improved.

KW - Clustering

KW - Different information sources

KW - Machine learning

KW - Music information retrieval

UR - http://www.scopus.com/inward/record.url?scp=63049086577&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=63049086577&partnerID=8YFLogxK

U2 - 10.1109/TMM.2009.2012942

DO - 10.1109/TMM.2009.2012942

M3 - Article

AN - SCOPUS:63049086577

VL - 11

SP - 477

EP - 484

JO - IEEE Transactions on Multimedia

JF - IEEE Transactions on Multimedia

SN - 1520-9210

IS - 3

M1 - 4797802

ER -