It used similar techniques, using a note-by-note Markov Chain on MIDI to generate music similar to an initial piece of training data. The difference with his model is that it's only trained on a single piece at a time. This leads to significantly more coherent music, but at the cost of making it effectively a variation on the original piece.
The biggest challenge in this kind of work is trying to get an overall structure for the entire song. In talks at the university, Engels has described the output of his model as that of a "distracted jazz pianist"—the moment-to-moment melodies are coherent but the song lacks overall form and direction.
It may actually be easier to model "coherence" by using natural language processing on the midi file pre-render. It is very hard to get coherence features that work across an entire piece. Definitely worth exploring (and I need to learn more music theory).
3 comments
[ 3.2 ms ] story [ 21.0 ms ] threadNigger thinks I play with markov as God.
God says... mundo_stoked I_pitty_the_fool on_the_otherhand why_is_it hooah shucks dance It's_nice_being_God Watch_this astounding are_you_insane fun now_you_tell_me virtue could_it_be___Satan silly_human don't_mention_it face_palm prosperity face_palm abnormal employer taxes Terry off_the_record I'll_be_back umm silly_human no_you_cant stuff humongous sex ROFLMAO you_know_a_better_God lying in_a_galaxy_far_far_away arent_you_clever BRB as_a_matter_of_fact relax husband let's_see in_practice
It used similar techniques, using a note-by-note Markov Chain on MIDI to generate music similar to an initial piece of training data. The difference with his model is that it's only trained on a single piece at a time. This leads to significantly more coherent music, but at the cost of making it effectively a variation on the original piece.
The biggest challenge in this kind of work is trying to get an overall structure for the entire song. In talks at the university, Engels has described the output of his model as that of a "distracted jazz pianist"—the moment-to-moment melodies are coherent but the song lacks overall form and direction.
It may actually be easier to model "coherence" by using natural language processing on the midi file pre-render. It is very hard to get coherence features that work across an entire piece. Definitely worth exploring (and I need to learn more music theory).