Music information retrieval with temporal features and timbre

Authors:
Angelina A. Tzacheva;Keith J. Bell
Affiliations:
University of South Carolina Upstate, Department of Informatics, Spartanburg, SC;University of South Carolina Upstate, Department of Informatics, Spartanburg, SC
Venue:
AMT'10 Proceedings of the 6th international conference on Active media technology
Year:
2010

Citing 2
Cited 0

Detecting Emotions in Classical Music from MIDI Files

ISMIS '09 Proceedings of the 18th International Symposium on Foundations of Intelligent Systems
The WEKA data mining software: an update

ACM SIGKDD Explorations Newsletter

Quantified Score

Hi-index	0.00

Visualization

Abstract

At a time when the quantity of music media surrounding us is rapidly increasing and the access to recordings as well as the amount of music files available on the Internet is constantly growing, the problem of building music recommendation systems is of great importance. In this work, we perform a study on automatic classification of musical instruments. We use monophonic sounds. The latter have successfully been classified in the past, with main focus on pitch. We propose new temporal features and incorporate timbre descriptors. The advantages of this approach are: preservation of temporal information and high classification accuracy.