The Kiki-Bouba Challenge: Algorithmic composition for content-based MIR Research & Development

Bob L. Sturm; Nick Collins

The Kiki-Bouba Challenge: Algorithmic composition for content-based MIR Research & Development

Bob L. Sturm, Nick Collins

Department of Architecture, Design and Media Technology

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

3 Citations (Scopus)

587 Downloads (Pure)

Abstract

We propose the “Kiki-Bouba Challenge” (KBC) for the re- search and development of content-based music informa- tion retrieval (MIR) systems. This challenge is unencum- bered by several problems typically encountered in MIR research: insufficient data, restrictive copyrights, imper- fect ground truth, a lack of specific criteria for classes (e.g., genre), a lack of explicit problem definition, and irrepro- ducibility. KBC provides a limitless amount of free data, a perfect ground truth, and well-specifiable and meaningful characteristics defining each class. These ideal conditions are made possible by open source algorithmic composition — a hitherto under-exploited resource for MIR.

Original language	English
Title of host publication	Proceedings of the 15th International Society for Music Information Retrieval Conference, ISMIR 2014
Number of pages	6
Publisher	dblp Computer Science Bibliography
Publication date	2014
Pages	21-26
Publication status	Published - 2014
Event	International Symposium on Music Information Retrieval: ISMIR - Taipei, Taiwan, Province of China Duration: 27 Oct 2014 → 31 Oct 2014

Conference

Conference	International Symposium on Music Information Retrieval
Country/Territory	Taiwan, Province of China
City	Taipei
Period	27/10/2014 → 31/10/2014

Access to Document

kikibouba20140717Submitted manuscript, 332 KB

AUB Link

Search for the material in Aalborg University Library's search engine

Greedy Sparse Approximation and the Automatic Description of Audio and Music Data
Sturm, B. L.
Technology and Production Independent Postdoc Center for Independent Research
01/01/2012 → …
Project: Research

Cite this

@inproceedings{22e3c1623de9417181ce09647afdea10,

title = "The Kiki-Bouba Challenge: Algorithmic composition for content-based MIR Research & Development",

abstract = "We propose the “Kiki-Bouba Challenge” (KBC) for the re- search and development of content-based music informa- tion retrieval (MIR) systems. This challenge is unencum- bered by several problems typically encountered in MIR research: insufficient data, restrictive copyrights, imper- fect ground truth, a lack of specific criteria for classes (e.g., genre), a lack of explicit problem definition, and irrepro- ducibility. KBC provides a limitless amount of free data, a perfect ground truth, and well-specifiable and meaningful characteristics defining each class. These ideal conditions are made possible by open source algorithmic composition — a hitherto under-exploited resource for MIR.",

author = "Sturm, {Bob L.} and Nick Collins",

year = "2014",

language = "English",

pages = "21--26",

booktitle = "Proceedings of the 15th International Society for Music Information Retrieval Conference, ISMIR 2014",

publisher = "dblp Computer Science Bibliography",

note = "International Symposium on Music Information Retrieval : ISMIR ; Conference date: 27-10-2014 Through 31-10-2014",

}

Sturm, BL & Collins, N 2014, The Kiki-Bouba Challenge: Algorithmic composition for content-based MIR Research & Development. in Proceedings of the 15th International Society for Music Information Retrieval Conference, ISMIR 2014. dblp Computer Science Bibliography, pp. 21-26, International Symposium on Music Information Retrieval, Taipei, Taiwan, Province of China, 27/10/2014. <http://composerprogrammer.com/kikibouba.html>

The Kiki-Bouba Challenge: Algorithmic composition for content-based MIR Research & Development. / Sturm, Bob L.; Collins, Nick.
Proceedings of the 15th International Society for Music Information Retrieval Conference, ISMIR 2014. dblp Computer Science Bibliography, 2014. p. 21-26.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - The Kiki-Bouba Challenge

T2 - International Symposium on Music Information Retrieval

AU - Sturm, Bob L.

AU - Collins, Nick

PY - 2014

Y1 - 2014

N2 - We propose the “Kiki-Bouba Challenge” (KBC) for the re- search and development of content-based music informa- tion retrieval (MIR) systems. This challenge is unencum- bered by several problems typically encountered in MIR research: insufficient data, restrictive copyrights, imper- fect ground truth, a lack of specific criteria for classes (e.g., genre), a lack of explicit problem definition, and irrepro- ducibility. KBC provides a limitless amount of free data, a perfect ground truth, and well-specifiable and meaningful characteristics defining each class. These ideal conditions are made possible by open source algorithmic composition — a hitherto under-exploited resource for MIR.

AB - We propose the “Kiki-Bouba Challenge” (KBC) for the re- search and development of content-based music informa- tion retrieval (MIR) systems. This challenge is unencum- bered by several problems typically encountered in MIR research: insufficient data, restrictive copyrights, imper- fect ground truth, a lack of specific criteria for classes (e.g., genre), a lack of explicit problem definition, and irrepro- ducibility. KBC provides a limitless amount of free data, a perfect ground truth, and well-specifiable and meaningful characteristics defining each class. These ideal conditions are made possible by open source algorithmic composition — a hitherto under-exploited resource for MIR.

M3 - Article in proceeding

SP - 21

EP - 26

BT - Proceedings of the 15th International Society for Music Information Retrieval Conference, ISMIR 2014

PB - dblp Computer Science Bibliography

Y2 - 27 October 2014 through 31 October 2014

ER -

The Kiki-Bouba Challenge: Algorithmic composition for content-based MIR Research & Development

Abstract

Conference

Access to Document

AUB Link

Fingerprint

Projects

Greedy Sparse Approximation and the Automatic Description of Audio and Music Data

Cite this