DocumentCode :
2506406
Title :
Selection of Training Instances for Music Genre Classification
Author :
Lopes, Miguel ; Gouyon, Fabien ; Koerich, Alessandro L. ; Oliveira, Luiz E S
Author_Institution :
INESC Porto, Porto, Portugal
fYear :
2010
fDate :
23-26 Aug. 2010
Firstpage :
4569
Lastpage :
4572
Abstract :
In this paper we present a method for the selection of training instances based on the classification accuracy of a SVM classifier. The instances consist of feature vectors representing short-term, low-level characteristics of music audio signals. The objective is to build, from only a portion of the training data, a music genre classifier with at least similar performance as when the whole data is used. The particularity of our approach lies in a pre-classification of instances prior to the main classifier training: i.e. we select from the training data those instances that show better discrimination with respect to class memberships. On a very challenging dataset of 900 music pieces divided among 10 music genres, the instance selection method slightly improves the music genre classification in 2.4 percentage points. On the other hand, the resulting classification model is significantly reduced, permitting much faster classification over test data.
Keywords :
audio signal processing; feature extraction; music; signal classification; support vector machines; SVM classifier; class membership; feature vectors; music audio signal; music genre classification; training instance selection; Accuracy; Multiple signal classification; Music; Music information retrieval; Support vector machines; Training; Training data; Bag-of-frame; Genre classification; MIR;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2010 20th International Conference on
Conference_Location :
Istanbul
ISSN :
1051-4651
Print_ISBN :
978-1-4244-7542-1
Type :
conf
DOI :
10.1109/ICPR.2010.1128
Filename :
5597374
Link To Document :
بازگشت