Harmonic Recomposition using Conditional Autoregressive Modeling
This work addresses music recomposition for creative applications, but it is incremental as it builds directly on prior methods.
The paper tackles the problem of music recomposition by applying a conditional autoregressive pipeline to generate diverse and structured music conditioned on chord sequences, based on existing methods.
We demonstrate a conditional autoregressive pipeline for efficient music recomposition, based on methods presented in van den Oord et al.(2017). Recomposition (Casal & Casey, 2010) focuses on reworking existing musical pieces, adhering to structure at a high level while also re-imagining other aspects of the work. This can involve reuse of pre-existing themes or parts of the original piece, while also requiring the flexibility to generate new content at different levels of granularity. Applying the aforementioned modeling pipeline to recomposition, we show diverse and structured generation conditioned on chord sequence annotations.