Improving MIDI-audio alignment with acoustic features

Articles:

Title:: Improving MIDI-audio alignment with acoustic features
Author(s):: Devaney, Johanna
Mandel, Michael I.
Ellis, Daniel P. W.
Date:: 2009
Type:: Articles
Department:: Electrical Engineering
Permanent URL:: http://hdl.handle.net/10022/AC:P:13655
Book/Journal Title:: 2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, October 18-21, 2009, Mohonk Mountain House, New Paltz, NY, USA
Publisher:: IEEE
Publisher Location:: Piscataway, N.J.
Abstract:: This paper describes a technique to improve the accuracy of dynamic time warping-based MIDI-audio alignment. The technique implements a hidden Markov model that uses aperiodicity and power estimates from the signal as observations and the results of a dynamic time warping alignment as a prior. In addition to improving the overall alignment, this technique also identifies the transient and steady state sections of the note. This information is important for describing various aspects of a musical performance, including both pitch and rhythm.
Subject(s):: Electrical engineering
Applied mathematics
DOI:: http://dx.doi.org/10.1109/ASPAA.2009.5346500