Loading...
Please wait, while we are loading the content...
Similar Documents
Iliopoulos: “Music genre classification via compressive sampling (2010)
| Content Provider | CiteSeerX |
|---|---|
| Author | Chang, Kaichun K. Jang, Jyh-Shing Roger Iliopoulos, Costas S. |
| Description | Compressive sampling (CS) is a new research topic in signal processing that has piqued the interest of a wide range of researchers in different fields recently. In this paper, we present a CS-based classifier for music genre classification, with two sets of features, including short-time and long-time features of audio music. The proposed classifier generates a compact signature to achieve a significant reduction in the dimensionality of the audio music signals. The experimental results demonstrate that the computation time of the CS-based classifier is only about 20 % of SVM on GTZAN dataset, with an accuracy of 92.7%. Several experiments were conducted in this study to illustrate the feasibility and robustness of the proposed methods as compared to other approaches. Proceedings of the 11th International Conference on Music Information Retrieval (ISMIR |
| File Format | |
| Language | English |
| Publisher Date | 2010-01-01 |
| Access Restriction | Open |
| Subject Keyword | Audio Music Gtzan Dataset Cs-based Classifier New Research Topic Compressive Sampling Audio Music Signal Significant Reduction Several Experiment Wide Range Computation Time Signal Processing Music Genre Classification Different Field Experimental Result Compact Signature Long-time Feature |
| Content Type | Text |
| Resource Type | Article |
