Generative AI for images and music produce pixels and waveform data, respectively. I wonder if there is research into "procedural" data; so in this case, it would be SVG elements and, perhaps, MIDI data respectively.
I know training data would be much more harder to get, (notwithstanding legal ramifications), but I think that creating structured, procedural data will be much more interesting than just the final, "raw" output!
I've thought about this too. The instruments themselves can be synthesized for extremely high quality audio. All we need is the musical structure - the MIDI.
I know training data would be much more harder to get, (notwithstanding legal ramifications), but I think that creating structured, procedural data will be much more interesting than just the final, "raw" output!