Harmonic Recomposition using Conditional Autoregressive Modeling
Sound
2018-11-20 v1 Machine Learning
Audio and Speech Processing
Machine Learning
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.
Cite
@article{arxiv.1811.07426,
title = {Harmonic Recomposition using Conditional Autoregressive Modeling},
author = {Kyle Kastner and Rithesh Kumar and Tim Cooijmans and Aaron Courville},
journal= {arXiv preprint arXiv:1811.07426},
year = {2018}
}
Comments
3 pages, 2 figures. In Proceedings of The Joint Workshop on Machine Learning for Music, ICML 2018