Two Data Sets for Tempo Estimation and Key Detection in Electronic Dance Music Annotated from User Corrections

Peter Knees; A. Faraldo; Perfecto Herrera; Richard Vogl; Sebastian Böck; Florian Hörschläger; M. Le Goff

Two Data Sets for Tempo Estimation and Key Detection in Electronic Dance Music Annotated from User Corrections

Peter Knees, A. Faraldo, Perfecto Herrera, Richard Vogl, Sebastian Böck, Florian Hörschläger, M. Le Goff

Institute of Computational Perception

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

We present two new data sets for automatic evaluation of tempo estimation and key detection algorithms. In contrast to existing collections, both released data sets focus on electronic dance music (EDM). The data sets have been automatically created from user feedback and annotations extracted from web sources. More precisely, we utilize user corrections submitted to an online forum to report wrong tempo and key annotations on the Beatport website. Beatport is a digital record store targeted at DJs and focusing on EDM genres. For all annotated tracks in the data sets, samples of at least one-minute-length can be freely downloaded. For key detection, further ground truth is extracted from expert annotations manually assigned to Beatport tracks for benchmarking purposes. The set for tempo estimation comprises 664 tracks and the set for key detection 604 tracks. We detail the creation process of both data sets and perform extensive benchmarks using state-of-theart algorithms from both academic research and commercial products. 1. I

Original language	English
Title of host publication	Proceedings of the 16th International Society for Music Information Retrieval Conference
Number of pages	7
Publication status	Published - Oct 2015

Fields of science

202002 Audiovisual media
102 Computer Sciences
102001 Artificial intelligence
102003 Image processing
102015 Information systems

JKU Focus areas

Computation in Informatics and Mathematics
Engineering and Natural Sciences (in general)

Cite this

@inproceedings{00792503e050411c880662baf84c583b,

title = "Two Data Sets for Tempo Estimation and Key Detection in Electronic Dance Music Annotated from User Corrections",

abstract = "We present two new data sets for automatic evaluation of tempo estimation and key detection algorithms. In contrast to existing collections, both released data sets focus on electronic dance music (EDM). The data sets have been automatically created from user feedback and annotations extracted from web sources. More precisely, we utilize user corrections submitted to an online forum to report wrong tempo and key annotations on the Beatport website. Beatport is a digital record store targeted at DJs and focusing on EDM genres. For all annotated tracks in the data sets, samples of at least one-minute-length can be freely downloaded. For key detection, further ground truth is extracted from expert annotations manually assigned to Beatport tracks for benchmarking purposes. The set for tempo estimation comprises 664 tracks and the set for key detection 604 tracks. We detail the creation process of both data sets and perform extensive benchmarks using state-of-theart algorithms from both academic research and commercial products. 1. I",

author = "Peter Knees and A. Faraldo and Perfecto Herrera and Richard Vogl and Sebastian B{\"o}ck and Florian H{\"o}rschl{\"a}ger and \{Le Goff\}, M.",

year = "2015",

month = oct,

language = "English",

booktitle = "Proceedings of the 16th International Society for Music Information Retrieval Conference",

}

TY - GEN

T1 - Two Data Sets for Tempo Estimation and Key Detection in Electronic Dance Music Annotated from User Corrections

AU - Knees, Peter

AU - Faraldo, A.

AU - Herrera, Perfecto

AU - Vogl, Richard

AU - Böck, Sebastian

AU - Hörschläger, Florian

AU - Le Goff, M.

PY - 2015/10

Y1 - 2015/10

N2 - We present two new data sets for automatic evaluation of tempo estimation and key detection algorithms. In contrast to existing collections, both released data sets focus on electronic dance music (EDM). The data sets have been automatically created from user feedback and annotations extracted from web sources. More precisely, we utilize user corrections submitted to an online forum to report wrong tempo and key annotations on the Beatport website. Beatport is a digital record store targeted at DJs and focusing on EDM genres. For all annotated tracks in the data sets, samples of at least one-minute-length can be freely downloaded. For key detection, further ground truth is extracted from expert annotations manually assigned to Beatport tracks for benchmarking purposes. The set for tempo estimation comprises 664 tracks and the set for key detection 604 tracks. We detail the creation process of both data sets and perform extensive benchmarks using state-of-theart algorithms from both academic research and commercial products. 1. I

AB - We present two new data sets for automatic evaluation of tempo estimation and key detection algorithms. In contrast to existing collections, both released data sets focus on electronic dance music (EDM). The data sets have been automatically created from user feedback and annotations extracted from web sources. More precisely, we utilize user corrections submitted to an online forum to report wrong tempo and key annotations on the Beatport website. Beatport is a digital record store targeted at DJs and focusing on EDM genres. For all annotated tracks in the data sets, samples of at least one-minute-length can be freely downloaded. For key detection, further ground truth is extracted from expert annotations manually assigned to Beatport tracks for benchmarking purposes. The set for tempo estimation comprises 664 tracks and the set for key detection 604 tracks. We detail the creation process of both data sets and perform extensive benchmarks using state-of-theart algorithms from both academic research and commercial products. 1. I

M3 - Conference proceedings

BT - Proceedings of the 16th International Society for Music Information Retrieval Conference

ER -