Towards Predicting Expressed Emotion in Music from Pairwise Comparisons

Jens Madsen; Bjørn Sand Jensen; Jan Larsen; Jens Brehm Nielsen

Towards Predicting Expressed Emotion in Music from Pairwise Comparisons

Jens Madsen, Bjørn Sand Jensen, Jan Larsen, Jens Brehm Nielsen

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

215 Downloads (Orbit)

Abstract

We introduce five regression models for the modeling of expressed emotion in music using data obtained in a two alternative forced choice listening experiment. The predictive performance of the proposed models is compared using learning curves, showing that all models converge to produce a similar classification error. The predictive ranking of the models is compared using Kendall's tau rank correlation coefficient which shows a difference despite similar classification error. The variation in predictions across subjects and the difference in ranking is investigated visually in the arousal-valence space and quantified using Kendall's tau.

Original language	English
Title of host publication	Proceedings of the 9th Sound and Music Computing Conference
Publication date	2012
Pages	350-357
Publication status	Published - 2012
Event	9th Sound and Music Computing Conference (SMC 2012) - Aalborg University Copenhagen, Copenhagen, Denmark Duration: 11 Jul 2012 → 14 Jul 2012 http://smc2012.smcnetwork.org/

Conference

Conference	9th Sound and Music Computing Conference (SMC 2012)
Location	Aalborg University Copenhagen
Country/Territory	Denmark
City	Copenhagen
Period	11/07/2012 → 14/07/2012
Internet address	http://smc2012.smcnetwork.org/

Bibliographical note

This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Access to Document

SMC2012Final published version, 374 KB

OpenUrl availability

Full text

Cite this

@inproceedings{3eec839c6cd24be6af0cc2048df10b50,

title = "Towards Predicting Expressed Emotion in Music from Pairwise Comparisons",

abstract = "We introduce five regression models for the modeling of expressed emotion in music using data obtained in a two alternative forced choice listening experiment. The predictive performance of the proposed models is compared using learning curves, showing that all models converge to produce a similar classification error. The predictive ranking of the models is compared using Kendall's tau rank correlation coefficient which shows a difference despite similar classification error. The variation in predictions across subjects and the difference in ranking is investigated visually in the arousal-valence space and quantified using Kendall's tau.",

author = "Jens Madsen and Jensen, \{Bj{\o}rn Sand\} and Jan Larsen and Nielsen, \{Jens Brehm\}",

note = "This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.; 9th Sound and Music Computing Conference (SMC 2012) ; Conference date: 11-07-2012 Through 14-07-2012",

year = "2012",

language = "English",

pages = "350--357",

booktitle = "Proceedings of the 9th Sound and Music Computing Conference",

url = "http://smc2012.smcnetwork.org/",

}

TY - GEN

T1 - Towards Predicting Expressed Emotion in Music from Pairwise Comparisons

AU - Madsen, Jens

AU - Jensen, Bjørn Sand

AU - Larsen, Jan

AU - Nielsen, Jens Brehm

N1 - This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

PY - 2012

Y1 - 2012

N2 - We introduce five regression models for the modeling of expressed emotion in music using data obtained in a two alternative forced choice listening experiment. The predictive performance of the proposed models is compared using learning curves, showing that all models converge to produce a similar classification error. The predictive ranking of the models is compared using Kendall's tau rank correlation coefficient which shows a difference despite similar classification error. The variation in predictions across subjects and the difference in ranking is investigated visually in the arousal-valence space and quantified using Kendall's tau.

AB - We introduce five regression models for the modeling of expressed emotion in music using data obtained in a two alternative forced choice listening experiment. The predictive performance of the proposed models is compared using learning curves, showing that all models converge to produce a similar classification error. The predictive ranking of the models is compared using Kendall's tau rank correlation coefficient which shows a difference despite similar classification error. The variation in predictions across subjects and the difference in ranking is investigated visually in the arousal-valence space and quantified using Kendall's tau.

M3 - Article in proceedings

SP - 350

EP - 357

BT - Proceedings of the 9th Sound and Music Computing Conference

T2 - 9th Sound and Music Computing Conference (SMC 2012)

Y2 - 11 July 2012 through 14 July 2012

ER -

Towards Predicting Expressed Emotion in Music from Pairwise Comparisons

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this