Integrating features from different sources for music information retrieval

Tao Li, Mitsunori Ogihara, Shenghuo Zhu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 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 both lyrics and acoustic data. In this paper, we present a clustering algorithm that integrates features from both sources to perform bimodal learning. The algorithm is 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 classifiers can be significantly improved and that artist similarity can be efficiently identified.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Conference on Data Mining, ICDM
Pages372-381
Number of pages10
DOIs
StatePublished - 2006
Externally publishedYes
Event6th International Conference on Data Mining, ICDM 2006 - Hong Kong, China
Duration: Dec 18 2006Dec 22 2006

Other

Other6th International Conference on Data Mining, ICDM 2006
CountryChina
CityHong Kong
Period12/18/0612/22/06

Fingerprint

Computer music
Information retrieval systems
Information retrieval
Clustering algorithms
Classifiers
Acoustics

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Li, T., Ogihara, M., & Zhu, S. (2006). Integrating features from different sources for music information retrieval. In Proceedings - IEEE International Conference on Data Mining, ICDM (pp. 372-381). [4053064] https://doi.org/10.1109/ICDM.2006.89

Integrating features from different sources for music information retrieval. / Li, Tao; Ogihara, Mitsunori; Zhu, Shenghuo.

Proceedings - IEEE International Conference on Data Mining, ICDM. 2006. p. 372-381 4053064.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, T, Ogihara, M & Zhu, S 2006, Integrating features from different sources for music information retrieval. in Proceedings - IEEE International Conference on Data Mining, ICDM., 4053064, pp. 372-381, 6th International Conference on Data Mining, ICDM 2006, Hong Kong, China, 12/18/06. https://doi.org/10.1109/ICDM.2006.89
Li T, Ogihara M, Zhu S. Integrating features from different sources for music information retrieval. In Proceedings - IEEE International Conference on Data Mining, ICDM. 2006. p. 372-381. 4053064 https://doi.org/10.1109/ICDM.2006.89
Li, Tao ; Ogihara, Mitsunori ; Zhu, Shenghuo. / Integrating features from different sources for music information retrieval. Proceedings - IEEE International Conference on Data Mining, ICDM. 2006. pp. 372-381
@inproceedings{f0f51ff965f74228a6faa6dde2e40f0f,
title = "Integrating features from different sources for music information retrieval",
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 both lyrics and acoustic data. In this paper, we present a clustering algorithm that integrates features from both sources to perform bimodal learning. The algorithm is 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 classifiers can be significantly improved and that artist similarity can be efficiently identified.",
author = "Tao Li and Mitsunori Ogihara and Shenghuo Zhu",
year = "2006",
doi = "10.1109/ICDM.2006.89",
language = "English (US)",
isbn = "0769527019",
pages = "372--381",
booktitle = "Proceedings - IEEE International Conference on Data Mining, ICDM",

}

TY - GEN

T1 - Integrating features from different sources for music information retrieval

AU - Li, Tao

AU - Ogihara, Mitsunori

AU - Zhu, Shenghuo

PY - 2006

Y1 - 2006

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 both lyrics and acoustic data. In this paper, we present a clustering algorithm that integrates features from both sources to perform bimodal learning. The algorithm is 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 classifiers can be significantly improved and that artist similarity can be efficiently identified.

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 both lyrics and acoustic data. In this paper, we present a clustering algorithm that integrates features from both sources to perform bimodal learning. The algorithm is 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 classifiers can be significantly improved and that artist similarity can be efficiently identified.

UR - http://www.scopus.com/inward/record.url?scp=49749146558&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=49749146558&partnerID=8YFLogxK

U2 - 10.1109/ICDM.2006.89

DO - 10.1109/ICDM.2006.89

M3 - Conference contribution

SN - 0769527019

SN - 9780769527017

SP - 372

EP - 381

BT - Proceedings - IEEE International Conference on Data Mining, ICDM

ER -