Model based optimization of music onset detection
Loading...
Date
2015
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In this paper a comprehensive online music onset detection algorithm
is introduced where - in contrast to many other relevant publications -
14 important algorithm parameters are optimized simultaneously. For
solving the optimization problem we derive an extensive tool for iterative
model based optimization.
In each iteration, a very time consuming evaluation has to be per-
formed on a large music data base. To speed up this procedure, the
expected performance of each newly proposed setting is estimated in a
pretest on a representative part of the data so that just very promising
points are evaluated on all data. We compare different variants of the
classical and the fast optimization strategies with respect to the F-values
of their best identified parameter settings. The performance of the fast
approach appears to be competitive with the classical one while saving
more than 80% of music piece evaluations on average.
Our best found parameter settings, both for online and offline onset
detection, are mainly in accordance with the usual choices in the state-
of-the art literature concerning, e.g., the spectral
flux detection function
or preferences for window length and overlap. However, we also found
unexpected results. For example, the adaptive whitening pre-processing
step showed no effect.
Description
Table of contents
Keywords
Onset Detection, Kriging, Instance Optimization, Model Based Optimization