Abstract | ||
---|---|---|
This work studies the task of automatic emotion detection in music. Music may evoke more than one different emotion at the same time. Single-label classification and regression cannot model this multiplicity. Therefore, this work focuses on multi-label classification approaches, where a piece of music may simultaneously belong to more than one class. Seven algorithms are experimentally compared for this task. Furthermore, the predictive power of several audio features is evaluated using a new multi-label feature selection method. Experiments are conducted on a set of 593 songs with six clusters of emotions based on the Tellegen-Watson-Clark model of affect. Results show that multi-label modeling is successful and provide interesting insights into the predictive quality of the algorithms and features. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1186/1687-4722-2011-426793 | EURASIP Journal on Audio, Speech, and Music Processing |
Keywords | Field | DocType |
multi-label classification, feature selection, music information retrieval | Classifier chains,Feature selection,Pattern recognition,Predictive power,Computer science,Multi-label classification,Speech recognition,Artificial intelligence,Machine learning | Conference |
Volume | Issue | ISSN |
2011 | 1 | 1687-4722 |
Citations | PageRank | References |
177 | 5.51 | 17 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Konstantinos Trohidis | 1 | 177 | 5.85 |
Grigorios Tsoumakas | 2 | 2653 | 116.75 |
G. Kalliris | 3 | 277 | 14.72 |
Ioannis P. Vlahavas | 4 | 775 | 92.68 |