DeepAI AI Chat
Log In Sign Up

Imposing higher-level Structure in Polyphonic Music Generation using Convolutional Restricted Boltzmann Machines and Constraints

by   Stefan Lattner, et al.

We introduce a method for imposing higher-level structure on generated, polyphonic music. A Convolutional Restricted Boltzmann Machine (C-RBM) as a generative model is combined with gradient descent constraint optimization to provide further control over the generation process. Among other things, this allows for the use of a "template" piece, from which some structural properties can be extracted, and transferred as constraints to newly generated material. The sampling process is guided with Simulated Annealing in order to avoid local optima, and find solutions that both satisfy the constraints, and are relatively stable with respect to the C-RBM. Results show that with this approach it is possible to control the higher level self-similarity structure, the meter, as well as tonal properties of the resulting musical piece while preserving its local musical coherence.


page 5

page 8

page 12

page 18


Modeling Musical Structure with Artificial Neural Networks

In recent years, artificial neural networks (ANNs) have become a univers...

Controllable deep melody generation via hierarchical music structure representation

Recent advances in deep learning have expanded possibilities to generate...

SDMuse: Stochastic Differential Music Editing and Generation via Hybrid Representation

While deep generative models have empowered music generation, it remains...

High-Level Control of Drum Track Generation Using Learned Patterns of Rhythmic Interaction

Spurred by the potential of deep learning, computational music generatio...

Learning Musical Relations using Gated Autoencoders

Music is usually highly structured and it is still an open question how ...

cMelGAN: An Efficient Conditional Generative Model Based on Mel Spectrograms

Analysing music in the field of machine learning is a very difficult pro...

Automatic compile-time synthesis of entropy-optimal Boltzmann samplers

We present a famework for the automatic compilation of multi-parametric ...