Index of /~echew/papers/ICS2005

 Name                    Last modified      Size  Description
 Parent Directory                             -   
 images/                 13-Jul-2004 23:56    -   
 reference.txt           25-May-2007 04:59  715   
 appendix.html           13-Jul-2004 22:57  2.1K  
 glossary.html           13-Jul-2004 23:55  2.9K  
 CVL-ics2005-revised.pdf 17-Aug-2004 16:42  426K  

In this directory is the PDF file for a paper titled

"Dance Music Classification Using Inner Metric Analysis --
A Computational Approach and Case Study Using 
101 Latin American Dances and National Anthems"

by Elaine Chew, Anja Volk (Fleischer) and Chia-Ying Lee 
{echew, avolk, leechiay}@usc.edu

The paper will be presented at the 
Informs Computing Society 2005 Conference on
The Next Wave in Computing, Optimization and Decision Technologies
Anapolis, Maryland.  January 5-7, 2005.

The paper will appear in
The Next Wave in Computing, Optimization and Decision Technologies
Proceedings of the 9th INFORMS Computer Society Conference
Eds Bruce Golden, S. Raghavan, Edward Wasil.  Kluwer.

The conference website is at 
http://www.informs.org/Conf/Computing05/

THE COMPLETE PAPER, text with figures, can be viewed as a PDF document.
Click on CVL-ics2005-revised.pdf if you wish to view the paper in PDF format.

--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--

"Dance Music Classification Using Inner Metric Analysis --
A Computational Approach and Case Study Using 
101 Latin American Dances and National Anthems"

by Elaine Chew, Anja Volk (Fleischer) and Chia-Ying Lee 
{echew, avolk, leechiay}@usc.edu

ABSTRACT: This paper introduces a method for music genre
classification using a computational model for Inner Metric Analysis.
Prior classification methods focussing on temporal features utilize
tempo (speed) and meter (periodicity) patterns and are unable to
distinguish between pieces in the same tempo and meter.  Inner Metric
Analysis reveals not only the periodicity patterns in the music, but
also the accent patterns peculiar to each musical genre.  These accent
patterns tend to correspond to perceptual groupings of the notes.  We
propose an algorithm that uses Inner Metric Analysis to map note onset
information to an accent profile that can then be compared to template
profiles generated from rhythm patterns typical of each genre.  The
music is classified as being from the genre whose accent profile is
most highly correlated with the sample profile.  The method has a
computational complexity of O(n^2), where n is the length of the query
excerpt.  We report and analyze the results of the algorithm when
applied to Latin American dance music and national anthems that are in
the same meter (4/4) and have similar tempo ranges.  We evaluate the
efficacy of the algorithm when using two variants on the model for
Inner Metric Analysis: the metric weight model and the spectral weight
model.  We find that the correct genre is either the top rank choice
or a close second rank choice in almost 80% of the test pieces.