Music artist style identification by semi-supervised learning from both lyrics and content

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

20 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. The approach for using a small set of labeled samples for the seed labeling to build classifiers that improve themselves using unlabeled data is presented. This approach is tested on a data set consisting of 43 artists and 56 albums using artist similarity provided by All Music Guide. Experimental results show that using such an approach the accuracy of artist similarity classifiers can be significantly improved and that artist similarity can be efficiently identified.

Original languageEnglish (US)
Title of host publicationACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia
Pages364-367
Number of pages4
StatePublished - 2004
Externally publishedYes
EventACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia - New York, NY, United States
Duration: Oct 10 2004Oct 16 2004

Other

OtherACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia
CountryUnited States
CityNew York, NY
Period10/10/0410/16/04

Fingerprint

Supervised learning
Classifiers
Computer music
Information retrieval systems
Information retrieval
Labeling
Seed
Acoustics

Keywords

  • Artist style
  • Lyrics
  • Semi-supervised learning

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Li, T., & Ogihara, M. (2004). Music artist style identification by semi-supervised learning from both lyrics and content. In ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia (pp. 364-367)

Music artist style identification by semi-supervised learning from both lyrics and content. / Li, Tao; Ogihara, Mitsunori.

ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia. 2004. p. 364-367.

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

Li, T & Ogihara, M 2004, Music artist style identification by semi-supervised learning from both lyrics and content. in ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia. pp. 364-367, ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia, New York, NY, United States, 10/10/04.
Li T, Ogihara M. Music artist style identification by semi-supervised learning from both lyrics and content. In ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia. 2004. p. 364-367
Li, Tao ; Ogihara, Mitsunori. / Music artist style identification by semi-supervised learning from both lyrics and content. ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia. 2004. pp. 364-367
@inproceedings{bc4bc9d3bca94b65ae43240181d4ac33,
title = "Music artist style identification by semi-supervised learning from both lyrics and content",
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. The approach for using a small set of labeled samples for the seed labeling to build classifiers that improve themselves using unlabeled data is presented. This approach is tested on a data set consisting of 43 artists and 56 albums using artist similarity provided by All Music Guide. Experimental results show that using such an approach the accuracy of artist similarity classifiers can be significantly improved and that artist similarity can be efficiently identified.",
keywords = "Artist style, Lyrics, Semi-supervised learning",
author = "Tao Li and Mitsunori Ogihara",
year = "2004",
language = "English (US)",
isbn = "1581138938",
pages = "364--367",
booktitle = "ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia",

}

TY - GEN

T1 - Music artist style identification by semi-supervised learning from both lyrics and content

AU - Li, Tao

AU - Ogihara, Mitsunori

PY - 2004

Y1 - 2004

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. The approach for using a small set of labeled samples for the seed labeling to build classifiers that improve themselves using unlabeled data is presented. This approach is tested on a data set consisting of 43 artists and 56 albums using artist similarity provided by All Music Guide. Experimental results show that using such an approach 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. The approach for using a small set of labeled samples for the seed labeling to build classifiers that improve themselves using unlabeled data is presented. This approach is tested on a data set consisting of 43 artists and 56 albums using artist similarity provided by All Music Guide. Experimental results show that using such an approach the accuracy of artist similarity classifiers can be significantly improved and that artist similarity can be efficiently identified.

KW - Artist style

KW - Lyrics

KW - Semi-supervised learning

UR - http://www.scopus.com/inward/record.url?scp=13444256090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=13444256090&partnerID=8YFLogxK

M3 - Conference contribution

SN - 1581138938

SN - 9781581138931

SP - 364

EP - 367

BT - ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia

ER -