V O R T R A G
**********************
Oesterreichisches Forschungsinstitut fuer Artificial Intelligence(OFAI) der OSGK
Freyung 6/6, A-1010 Wien
Tel: +43-1-5336112-17, Fax: +43-1-5336112-77, Email: sec@ofai.at
Luis Jure, Lic
Full Professor
Escuela Universitaria de Música
Universidad de la República, Uruguay
http://www.eumus.edu.uy/eme/
https://iie.fing.edu.uy/investigacion/grupos/gpa/
"RHYTHMIC PATTERN ANALYSIS: THE URUGUAYAN CANDOMBE DRUMMING AS A CASE STUDY"
Computational analysis of the rhythmic/metrical structure of music
from audio signals is a well-known and important research topic in
music information retrieval. Most existing automatic methods follow a
bottom-up approach with little prior knowledge about the genre of the
music under analysis. Therefore, their attainable performance is
limited: they are typically unable to cope with music outside the
western music tradition, exhibiting for instance syncopation or
polyrhythmics. In this work, the Uruguayan Candombe drumming, an
afro-rooted rhythm from Latin America, is considered as a case study.
The characteristics that make it troublesome for typical algorithmic
approaches are analysed and its repetitive rhythmic patterns are
described. Then a supervised scheme for rhythmic pattern tracking
aiming at finding the metric structure from an audio signal, including
the phase of the beat, is proposed to tackle the Candombe analysis.
The performance of the method is evaluated and compared with those of
other beat tracking algorithms through a set of experiments involving
synthetic sample-based audio signals as well as excerpts from real
music recordings. The results of this work highlight the need for
style-specific techniques for music analysis, particularly for
non-western genres, and point out some directions for future research.
*********
Time: Tuesday, 19th November 2013, 6.30 p.m. sharp
Location: Oesterreichisches Forschungsinstitut
fuer Artificial Intelligence, OFAI
Freyung 6, Stiege 6, 1010 Wien
OESTERREICHISCHES FORSCHUNGSINSTITUT
FUER ARTIFICIAL INTELLIGENCE
Univ.-Prof. Ing. Dr. Robert Trappl
*********