Home

Support Vector Machine Active Learning for Music Retrieval

Michael I. Mandel; Graham E. Poliner; Daniel P. W. Ellis

Title:
Support Vector Machine Active Learning for Music Retrieval
Author(s):
Mandel, Michael I.
Poliner, Graham E.
Ellis, Daniel P. W.
Date:
Type:
Articles
Department:
Electrical Engineering
Volume:
12
Permanent URL:
Book/Journal Title:
Multimedia Systems
Abstract:
Searching and organizing growing digital music collections requires a computational model of music similarity. This paper describes a system for performing flexible music similarity queries using SVM active learning. We evaluated the success of our system by classifying 1210 pop songs according to mood and style (from an online music guide) and by the performing artist. In comparing a number of representations for songs, we found the statistics of mel-frequency cepstral coefficients to perform best in precision-at-20 comparisons. We also show that by choosing training examples intelligently, active learning requires half as many labeled examples to achieve the same accuracy as a standard scheme.
Subject(s):
Artificial intelligence
Music
Publisher DOI:
http://dx.doi.org/10.1007/s00530-006-0032-2
Item views:
81
Metadata:
View

In Partnership with the Center for Digital Research and Scholarship at Columbia University Libraries/Information Services.