Abstract
We describe a sequential neural network for harmonizing melodies in real time. It models aspects of human cognition. This neural network succeeds reasonably well, if we take into consideration constraints the imposed by real time processing. The model exploits efficiently the available sequential information. The net contains a sub-net for meter that produces a periodic index of meter, providing the needed metric awareness. The net learns the relations between important notes of the melody and their harmonies and is able to produce harmonies for new melodies in real time, i.e., without knowledge of the future development of the melody.
Original language | English |
---|---|
Journal | International Computer Music Conference, ICMC Proceedings |
State | Published - 1997 |
Event | 23rd International Computer Music Conference, ICMC 1997 - Thessaloniki, Greece Duration: 25 Sep 1997 → 30 Sep 1997 |
Bibliographical note
Publisher Copyright:© 1997 International Computer Music Conference, ICMC Proceedings. All rights reserved.