Does anyone know of an online resource where I can find stochastic matrices for an nth order Markov chain describing the probability of a note being played based on the previous n notes (for different musical genres, if possible)? I am looking for something similar to the second-order matrix found on this page: http://algorithmiccomposer.com/2010/04/openmusic-markov-chains-and-omlea.html
If not, or otherwise, what would be the best way to construct such a matrix for each genre? The article states that this can be done by hand or by analysing existing pieces of music. How could large amounts of music for each genre be processed to generate these matrices?
I have been doing research on this topic. The matrix you are looking for is highly dependant upon what kind of music you want to generate.
One of the people I work with wrote this paper that is the method used for this. It is based on using viewpoint to look at the music and then basically creating a transition matrix for all these viewpoints: http://www.ehu.es/cs-ikerbasque/conklin/papers/jnmr95.pdf
You can contact me if you need more specific info or collaboration.