Part of Advances in Neural Information Processing Systems 10 (NIPS 1997)
Dominik Hörnel
MELONET I is a multi-scale neural network system producing baroque-style melodic variations. Given a melody, the system in(cid:173) vents a four-part chorale harmonization and a variation of any chorale voice, after being trained on music pieces of composers like J. S. Bach and J . Pachelbel. Unlike earlier approaches to the learn(cid:173) ing of melodic structure, the system is able to learn and reproduce high-order structure like harmonic, motif and phrase structure in melodic sequences. This is achieved by using mutually interacting feedforward networks operating at different time scales, in combi(cid:173) nation with Kohonen networks to classify and recognize musical structure. The results are chorale partitas in the style of J. Pachel(cid:173) bel. Their quality has been judged by experts to be comparable to improvisations invented by an experienced human organist.