Article ID: | iaor20071437 |
Country: | United States |
Volume: | 18 |
Issue: | 3 |
Start Page Number: | 321 |
End Page Number: | 338 |
Publication Date: | Jun 2006 |
Journal: | INFORMS Journal On Computing |
Authors: | Franklin Judy A. |
Keywords: | music |
Some researchers in the computational sciences have considered music computation, including music reproduction and generation, as a dynamic system, i.e., a feedback process. The key element is that the state of the musical system depends on a history of past states. Recurrent (neural) networks have been deployed as models for learning musical processes. We first present a tutorial discussion of recurrent networks, covering those that have been used for music learning. Following this, we examine a thread of development of these recurrent networks for music computation that shows how more intricate music has been learned as the state of the art in recurrent networks improves. We present our findings that show that a long short-term memory recurrent network, with new representations that include music knowledge, can learn musical tasks, and can learn to reproduce long songs. Then, given a reharmonization of the chordal structure, it can generate an improvisation.