Abstract
In this paper we propose a feature set for emotion classification of Western popular music. We show that by surveying a range of common feature extraction methods, a set of five features can model emotion with good accuracy. To evaluate the system we implement an independent feature evaluation paradigm aimed at testing the property of generalizability; the ability of a machine learning algorithm to maintain good performance over different data sets.
| Original language | English |
|---|---|
| Title of host publication | The 9th International Symposium on Computer Music Modeling and Retrieval (CMMR) Music and Emotions |
| Publisher | Springer-Verlag |
| Pages | 508-517 |
| Number of pages | 10 |
| Publication status | Published - Jun 2012 |
Publication series
| Name | Lecture Notes in Computer Sciences |
|---|---|
| Publisher | Springer |
Fingerprint
Keywords
- music emotion classification
- popular music
- support vector machine
Cite this
Beveridge, S., & Knox, D. (2012). A feature survey for emotion classification of western popular music. In The 9th International Symposium on Computer Music Modeling and Retrieval (CMMR) Music and Emotions (pp. 508-517). (Lecture Notes in Computer Sciences ). Springer-Verlag. http://www.cmmr2012.eecs.qmul.ac.uk/