CITATION — REFERENCE ENTRY
Counterpoint by convolution — Proceedings of the 18th International Society for Music Information Retrieval Conference
- Key
- huang2017-coconet
- Authors
- Huang, Cheng-Zhi Anna; Cooijmans, Tim; Roberts, Adam; Courville, Aaron; Eck, Douglas
- Issued
- 2017
- Type
- paper-conference
- Container
- Proceedings of the 18th International Society for Music Information Retrieval Conference
Raw CSL JSON
{
"URL": "https://arxiv.org/abs/1903.07227",
"type": "paper-conference",
"title": "Counterpoint by convolution",
"author": [
{
"given": "Cheng-Zhi Anna",
"family": "Huang"
},
{
"given": "Tim",
"family": "Cooijmans"
},
{
"given": "Adam",
"family": "Roberts"
},
{
"given": "Aaron",
"family": "Courville"
},
{
"given": "Douglas",
"family": "Eck"
}
],
"issued": {
"date-parts": [
[
2017
]
]
},
"event-place": "Suzhou, China",
"container-title": "Proceedings of the 18th International Society for Music Information Retrieval Conference"
}
Claims
-
Coconet is a convolutional neural network trained to complete partial musical scores, using blocked Gibbs sampling as an analogue of rewriting so that it is not tied to composing from beginning to end; the authors note that human composers work nonlinearly and that rules of counterpoint can contradict each other.
"Machine learning models of music typically break up the task of composition into a chronological process, composing a piece of music in a single pass from beginning to end. On the contrary, human composers write music in a nonlinear fashion, scribbling motifs here and there, often revisiting choices previously made. In order to better approximate this process, we train a convolutional neural network to complete partial musical scores, and explore the use of blocked Gibbs sampling as an analogue to rewriting. [...] Human composers have developed systems of rules to guide their compositional decisions. However, these rules sometimes contradict each other"
Available in