Abstract
The ability of gifted composers like Mozart to create complex multipart musical compositions with relative ease suggests a highly efficient mechanism for generating multiple parts simultaneously. Computational modelsofhumanmusiccompositioncanpotentiallyshedlightonhowsuchrapidcreativityispossible.This article proposes such a model based on the idea that the multiple threads of a song are temporal patterns that are functionally related, which means that one instrument's sequence is a function of another's. This idea is implemented in a program called NEAT Drummer that interactively evolves a type of artificial neural network called a compositional pattern-producing network, which represents the functional relationship between the instruments and drums. The main result is that richly textured drum tracks that tightly follow the structure of the original song are easily generated because of their functional relationship to it.
Original language | English (US) |
---|---|
Pages (from-to) | 227-251 |
Number of pages | 25 |
Journal | Connection Science |
Volume | 21 |
Issue number | 2-3 |
DOIs | |
State | Published - 2009 |
Externally published | Yes |
All Science Journal Classification (ASJC) codes
- Software
- Human-Computer Interaction
- Artificial Intelligence
Keywords
- CPPNs
- Compositional pattern-producing networks
- Computer-generated music
- IEC
- Interactive evolutionary computation
- NeuroEvolution of Augmenting Topologies