Harmonising Chorales by Probabilistic Inference
Abstract
We describe how we used a data set of chorale harmonisations composed by Johann Sebastian Bach to train Hidden Markov Models. Using a prob- abilistic framework allows us to create a harmonisation system which learns from examples, and which can compose new harmonisations. We make a quantitative comparison of our system's harmonisation perfor- mance against simpler models, and provide example harmonisations.
Cite
Text
Allan and Williams. "Harmonising Chorales by Probabilistic Inference." Neural Information Processing Systems, 2004.Markdown
[Allan and Williams. "Harmonising Chorales by Probabilistic Inference." Neural Information Processing Systems, 2004.](https://mlanthology.org/neurips/2004/allan2004neurips-harmonising/)BibTeX
@inproceedings{allan2004neurips-harmonising,
title = {{Harmonising Chorales by Probabilistic Inference}},
author = {Allan, Moray and Williams, Christopher},
booktitle = {Neural Information Processing Systems},
year = {2004},
pages = {25-32},
url = {https://mlanthology.org/neurips/2004/allan2004neurips-harmonising/}
}