Loading...
A multi-genre model for music emotion recognition using linear regressors
Griffiths, Darryl Cunningham, Stuart Weinel, Jonathan Picking, Richard
Griffiths, Darryl
Cunningham, Stuart
Weinel, Jonathan
Picking, Richard
Advisors
Editors
Other Contributors
EPub Date
Publication Date
2021-09-21
Submitted Date
Collections
Files
Loading...
Article
Adobe PDF, 858.88 KB
Other Titles
Enhancing film sound design using audio features, regression models and artificial neural networks
Abstract
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 (nā=ā44) identified audio features that map to arousal and valence for 20 songs. From this, we constructed a set of linear regressors. The second study (nā=ā158) 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.
Citation
Griffiths, D., Cunningham, S., Weinel, J., & Picking, R. (2021). A multi-genre model for music emotion recognition using linear regressors. Journal of New Music Research, 50(4), 355-372. https://doi.org/10.1080/09298215.2021.1977336
Publisher
Taylor & Francis
Journal
Journal of New Music Research
Research Unit
DOI
10.1080/09298215.2021.1977336
PubMed ID
PubMed Central ID
Type
Article
Language
Description
This is an Accepted Manuscript of an article published by Taylor & Francis in Journal of New Music Research on 21/09/2021, available online: https://doi.org/10.1080/09298215.2021.1977336
Series/Report no.
ISSN
0929-8215
EISSN
1744-5027