Note detection with dynamic bayesian networks as a postanalysis step for NMF-based multiple pitch estimation techniques

In this paper we present a method for detecting note events in the note activity matrix obtained with Nonnegative Matrix Factorization, currently the most common method for multipitch analysis. Postprocessing of this matrix is usually neglected by other authors, who use a simple thresholding, often paired with additional heuristics. We propose a theoretically-grounded probabilistic model and obtain very promising results due to the fact that it was able to capture basic musicological information. The biggest advantage of our approach is that it can be extended without much effort to include various information about musical signals, such as principles of tonality and rhythm.