Thanks! Will have a read through.
I often wonder if we could develop software to make chord/harmony discovery easier when arranging a melody. At the moment it's down to a combination of knowledge of music theory, intuition and trial and error.
I'm talking about more advanced harmony constructions like Jacob Colliers work (check him out if you haven't heard)-
Harmony (and it's relation to melody) is a time based problem, you can't just join random chords together that match the current melody note. LSTM works for time series learning but I am not convinced it "gets" concepts of music theory, so maybe some kind of hybrid of engineered music theory features + LSTM with good training material could work
I'm talking about more advanced harmony constructions like Jacob Colliers work (check him out if you haven't heard)-
https://youtu.be/SM2nhLSeJXg
http://brightonjazzschool.com/jacob-collier-masterclass/
Harmony (and it's relation to melody) is a time based problem, you can't just join random chords together that match the current melody note. LSTM works for time series learning but I am not convinced it "gets" concepts of music theory, so maybe some kind of hybrid of engineered music theory features + LSTM with good training material could work