Chia-Ying Lee / Previous Work

Dance Music Classification With Inner Metrix Analysis

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. ICS2005, Annapolis, MD, Jan 5-7, 2005.

This is an algorithm about classifying dance music (ex. Tango, Salsa...etc) with its rhythm patterns. By using Inner Metric Analysis, we are able to generate an accent profile for an arbitrary rhythm pattern that can then be compared with typical template profiles from each dance music genre. Music is classified to the genre with which its accent profile is most highly correlated.

We found that the correct genre is either the top rank choice or a close second rank choice in almost 80% of the test pieces.

> download PDF

Structural Analysis of Musical Rhythm: A Comprehensive Review

Chia-Ying Lee, Cheng-Yuan Liou

Technical Report NSC 92-2213-E-002-002, 2003, CSIE NTU

We reviewed the previous work by H. C. Longuet-Higgins and described a new representation for rhythms with Lindenmayer system (L-system). L-system was originally designed to model plant development by using bracketed strings and rewriting rules. We used the expression capability of L-system to depict the hierarchical structures in rhythms. A rhythm can then be described in any level of its hierarchy like a zoom-in and zoom-out scope.