Modeling Expressed Emotions in Music using Pairwise Comparisons

Publication: Research - peer-reviewArticle in proceedings – Annual report year: 2012

Standard

Modeling Expressed Emotions in Music using Pairwise Comparisons. / Madsen, Jens; Nielsen, Jens Brehm; Jensen, Bjørn Sand; Larsen, Jan.

9th International Symposium on Computer Music Modelling and Retrieval (CMMR 2012). Queen Mary University of London, 2012. p. 526-533.

Publication: Research - peer-reviewArticle in proceedings – Annual report year: 2012

Harvard

Madsen, J, Nielsen, JB, Jensen, BS & Larsen, J 2012, 'Modeling Expressed Emotions in Music using Pairwise Comparisons'. in 9th International Symposium on Computer Music Modelling and Retrieval (CMMR 2012). Queen Mary University of London, pp. 526-533.

APA

Madsen, J., Nielsen, J. B., Jensen, B. S., & Larsen, J. (2012). Modeling Expressed Emotions in Music using Pairwise Comparisons. In 9th International Symposium on Computer Music Modelling and Retrieval (CMMR 2012). (pp. 526-533). Queen Mary University of London.

CBE

Madsen J, Nielsen JB, Jensen BS, Larsen J. 2012. Modeling Expressed Emotions in Music using Pairwise Comparisons. In 9th International Symposium on Computer Music Modelling and Retrieval (CMMR 2012). Queen Mary University of London. pp. 526-533.

MLA

Madsen, Jens et al. "Modeling Expressed Emotions in Music using Pairwise Comparisons". 9th International Symposium on Computer Music Modelling and Retrieval (CMMR 2012). Queen Mary University of London. 2012. 526-533.

Vancouver

Madsen J, Nielsen JB, Jensen BS, Larsen J. Modeling Expressed Emotions in Music using Pairwise Comparisons. In 9th International Symposium on Computer Music Modelling and Retrieval (CMMR 2012). Queen Mary University of London. 2012. p. 526-533.

Author

Madsen, Jens; Nielsen, Jens Brehm; Jensen, Bjørn Sand; Larsen, Jan / Modeling Expressed Emotions in Music using Pairwise Comparisons.

9th International Symposium on Computer Music Modelling and Retrieval (CMMR 2012). Queen Mary University of London, 2012. p. 526-533.

Publication: Research - peer-reviewArticle in proceedings – Annual report year: 2012

Bibtex

@inbook{4821eb6d49a345909bcf6edf9238bc81,
title = "Modeling Expressed Emotions in Music using Pairwise Comparisons",
publisher = "Queen Mary University of London",
author = "Jens Madsen and Nielsen, {Jens Brehm} and Jensen, {Bjørn Sand} and Jan Larsen",
year = "2012",
pages = "526-533",
booktitle = "9th International Symposium on Computer Music Modelling and Retrieval (CMMR 2012)",

}

RIS

TY - GEN

T1 - Modeling Expressed Emotions in Music using Pairwise Comparisons

A1 - Madsen,Jens

A1 - Nielsen,Jens Brehm

A1 - Jensen,Bjørn Sand

A1 - Larsen,Jan

AU - Madsen,Jens

AU - Nielsen,Jens Brehm

AU - Jensen,Bjørn Sand

AU - Larsen,Jan

PB - Queen Mary University of London

PY - 2012

Y1 - 2012

N2 - We introduce a two-alternative forced-choice experimental paradigm to quantify expressed emotions in music using the two wellknown arousal and valence (AV) dimensions. In order to produce AV scores from the pairwise comparisons and to visualize the locations of excerpts in the AV space, we introduce a flexible Gaussian process (GP) framework which learns from the pairwise comparisons directly. A novel dataset is used to evaluate the proposed framework and learning curves show that the proposed framework needs relative few comparisons in order to achieve satisfactory performance. This is further supported by visualizing the learned locations of excerpts in the AV space. Finally, by examining the predictive performance of the user-specific models we show the importance of modeling subjects individually due to significant subjective differences.

AB - We introduce a two-alternative forced-choice experimental paradigm to quantify expressed emotions in music using the two wellknown arousal and valence (AV) dimensions. In order to produce AV scores from the pairwise comparisons and to visualize the locations of excerpts in the AV space, we introduce a flexible Gaussian process (GP) framework which learns from the pairwise comparisons directly. A novel dataset is used to evaluate the proposed framework and learning curves show that the proposed framework needs relative few comparisons in order to achieve satisfactory performance. This is further supported by visualizing the learned locations of excerpts in the AV space. Finally, by examining the predictive performance of the user-specific models we show the importance of modeling subjects individually due to significant subjective differences.

BT - 9th International Symposium on Computer Music Modelling and Retrieval (CMMR 2012)

T2 - 9th International Symposium on Computer Music Modelling and Retrieval (CMMR 2012)

SP - 526

EP - 533

ER -