Jump to content

Counterfactuals in music generation

From CCRMA Wiki
Revision as of 00:02, 21 April 2021 by Agrawalk (talk | contribs) (Added 4/20 update.)

4/20/21: Still playing around with the generative models, trying to get some intuition into their workings and what parameters I can adjust. The orderless composition property of Coconet is particularly interesting — it seems like the sampling strategy is non-deterministic, and we could run a counterfactual in the vein of "what would have happened if the notes were generated in a different order..."

4/15/21: this week, I tentatively narrowed the scope of the project to music generation. I have been experimenting with various music generation models from Google Magenta, including the Music Transformer and CoCoNet.