A multi-genre model for music emotion recognition using linear regressors

Making the link between human emotion and music is challenging. Our aim was to produce an efficient system that emotionally rates songs from multiple genres. To achieve this, we employed a series of online self-report studies, utilising Russell's circumplex model. The first study (n = 44) ident...

Full description

Saved in:
Bibliographic Details
Published in:Journal of new music research Vol. 50; no. 4; pp. 355 - 372
Main Authors: Griffiths, Darryl, Cunningham, Stuart, Weinel, Jonathan, Picking, Richard
Format: Journal Article
Language:English
Published: Abingdon Routledge 08.08.2021
Taylor & Francis Ltd
Subjects:
Arousal
emotion
Emotion recognition
Emotions
MER
Music
perception
regression
valence
ISSN:0929-8215, 1744-5027
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Making the link between human emotion and music is challenging. Our aim was to produce an efficient system that emotionally rates songs from multiple genres. To achieve this, we employed a series of online self-report studies, utilising Russell's circumplex model. The first study (n = 44) identified audio features that map to arousal and valence for 20 songs. From this, we constructed a set of linear regressors. The second study (n = 158) measured the efficacy of our system, utilising 40 new songs to create a ground truth. Results show our approach may be effective at emotionally rating music, particularly in the prediction of valence.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0929-8215
1744-5027
DOI:10.1080/09298215.2021.1977336