Recurrent Neural Networks for Music Computation

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...

Full description

Saved in:
Bibliographic Details
Published in:INFORMS journal on computing 2006-06, Vol.18 (3), p.321-338
Main Author: Franklin, Judy A
Format: Article
Language:English
Subjects:
computer music
Forecasts and trends
LSTM
Music
music representation
Neural networks
recurrent neural networks
Recursion theory
Studies
Study and teaching
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1091-9856
1526-5528
1091-9856
DOI:10.1287/ijoc.1050.0131