Abstract | ||
---|---|---|
We describe an approach to the combination of music sim- ilarity feature spaces in the context of music classificatio n. The approach is based on taking the product of posterior probabilities obtained from separate classifiers for the di f- ferent feature spaces. This allows for a different influence of the classifiers per song and an overall classification accura cy improving those resulting from individual feature spaces alone. This is demonstrated by combining spectral and rhythmic similarity for classification of ballroom dance music. |
Year | Venue | Keywords |
---|---|---|
2006 | ISMIR 2013 | combination,music classification,feature space,posterior probability |
Field | DocType | Citations |
Electronic dance music,Pattern recognition,Computer science,Speech recognition,Posterior probability,Artificial intelligence,Probabilistic logic,Ballroom,Rhythm,Machine learning | Conference | 16 |
PageRank | References | Authors |
1.31 | 12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Arthur Flexer | 1 | 599 | 48.03 |
Fabien Gouyon | 2 | 103 | 8.54 |
Simon Dixon | 3 | 1164 | 107.57 |
Widmer Gerhard | 4 | 2619 | 240.02 |