School of Informatics | Music Information Processing: Symbolic
I546 | 29037 | Raphael

This course deals with both methodology and specific applications
that attempt to algorithmically annotate, understand, recognize, and
categorize music in symbolic (score like) form. Particular
applications will include key finding, harmonic analysis, note
spelling, rhythm recognition, meter induction, piano fingering, and
various classification problems such as genre or composer
identification. The methodology we will employ will be probabilistic
and will include ideas from Machine Learning such as optimal
classifiers, hidden Markov models, and Bayesian networks. Students
will have computing assignments, present papers, and be expected to
implement solutions to problems using a high-level language such as
R or Matlab.