TY - GEN
T1 - Music genre classification using multiscale scattering and sparse representations
AU - Chen, Xu
AU - Ramadge, Peter J.
PY - 2013
Y1 - 2013
N2 - An effective music genre classication approach is proposed that combines the translation-invariance and deformation-robustness property of scattering coefficients and the discriminative power of sparse representation-based classifiers. We argue that these two approaches to feature selection and classification complement each other in reducing the in-class variability of data, and this should lead to enhanced performance. Our results show clear improvement over a variety of previous approaches. A music genre classication accuracy of approximately 91.2% on the GTZAN database is reported.
AB - An effective music genre classication approach is proposed that combines the translation-invariance and deformation-robustness property of scattering coefficients and the discriminative power of sparse representation-based classifiers. We argue that these two approaches to feature selection and classification complement each other in reducing the in-class variability of data, and this should lead to enhanced performance. Our results show clear improvement over a variety of previous approaches. A music genre classication accuracy of approximately 91.2% on the GTZAN database is reported.
UR - http://www.scopus.com/inward/record.url?scp=84881526300&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84881526300&partnerID=8YFLogxK
U2 - 10.1109/CISS.2013.6552324
DO - 10.1109/CISS.2013.6552324
M3 - Conference contribution
AN - SCOPUS:84881526300
SN - 9781467352376
T3 - 2013 47th Annual Conference on Information Sciences and Systems, CISS 2013
BT - 2013 47th Annual Conference on Information Sciences and Systems, CISS 2013
T2 - 2013 47th Annual Conference on Information Sciences and Systems, CISS 2013
Y2 - 20 March 2013 through 22 March 2013
ER -