Conference paper Open Access

Parameterized Melody Generation with Autoencoders and Temporally-Consistent Noise

Weber, Aline; Alegre, Lucas Nunes; Torresen, Jim; da Silva, Bruno C.

We introduce a machine learning technique to autonomously generate novel melodies that are variations of an arbitrary base melody. These are produced by a neural network that ensures that (with high probability) the melodic and rhythmic structure of the new melody is consistent with a given set of sample songs. We train a Variational Autoencoder network to identify a low-dimensional set of variables that allows for the compression and representation of sample songs. By perturbing these variables with Perlin Noise---a temporally-consistent parameterized noise function---it is possible to generate smoothly-changing novel melodies. We show that (1) by regulating the amount of noise, one can specify how much of the base song will be preserved; and (2) there is a direct correlation between the noise signal and the differences between the statistical properties of novel melodies and the original one. Users can interpret the controllable noise as a type of "creativity knob": the higher it is, the more leeway the network has to generate significantly different melodies. We present a physical prototype that allows musicians to use a keyboard to provide base melodies and to adjust the network's "creativity knobs" to regulate in real-time the process that proposes new melody ideas.

Files (1.3 MB)
Name Size
1.3 MB Download
All versions This version
Views 3333
Downloads 2727
Data volume 35.6 MB35.6 MB
Unique views 3030
Unique downloads 2424


Cite as