Study and evaluation of music beat tracking algorithms
Manuel Florencio Olmedo
Degree on sound and image engineering
Polytechnic School. University of Alicante.
A music beat tracker is a procedure that is able to extract the times where a human would clap or tap when he or she listens to a piece of music. Automatic transcription of music genre classification use extensively this kind of information for improve their results. Onset detection is an important tool for beat tracking, as well. The aim of this work is to study a number of beat trackers in order to compare them when they are applied to different kinds of musical sounds. An improvement has been proposed to one of them after analyse its behaviour.
Technical report (in spanish)
A number of degree students are doing their academic works in our group
in diferent tasks related to pattern recognition and artificial intelligence research and development. You can
to know more about some of those projects.