SOTAVerified

Harmonic Recomposition using Conditional Autoregressive Modeling

2018-11-18Code Available0· sign in to hype

Kyle Kastner, Rithesh Kumar, Tim Cooijmans, Aaron Courville

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

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.

Reproductions