Bach in a Box - Real-Time Harmony
Abstract
We describe a system for learning J. S. Bach's rules of musical har(cid:173) mony. These rules are learned from examples and are expressed as rule-based neural networks. The rules are then applied in real(cid:173) time to generate new accompanying harmony for a live performer. Real-time functionality imposes constraints on the learning and harmonizing processes, including limitations on the types of infor(cid:173) mation the system can use as input and the amount of processing the system can perform. We demonstrate algorithms for gener(cid:173) ating and refining musical rules from examples which meet these constraints. We describe a method for including a priori knowl(cid:173) edge into the rules which yields significant performance gains. We then describe techniques for applying these rules to generate new music in real-time. We conclude the paper with an analysis of experimental results.
Cite
Text
Spangler et al. "Bach in a Box - Real-Time Harmony." Neural Information Processing Systems, 1997.Markdown
[Spangler et al. "Bach in a Box - Real-Time Harmony." Neural Information Processing Systems, 1997.](https://mlanthology.org/neurips/1997/spangler1997neurips-bach/)BibTeX
@inproceedings{spangler1997neurips-bach,
title = {{Bach in a Box - Real-Time Harmony}},
author = {Spangler, Randall R. and Goodman, Rodney M. and Hawkins, Jim},
booktitle = {Neural Information Processing Systems},
year = {1997},
pages = {957-963},
url = {https://mlanthology.org/neurips/1997/spangler1997neurips-bach/}
}