Imposing higher-level Structure in Polyphonic Music Generation using Convolutional Restricted Boltzmann Machines and Constraints
This work addresses the challenge of generating structured polyphonic music for applications in music composition and AI creativity, representing an incremental improvement over existing generative methods.
The authors tackled the problem of controlling higher-level structure in polyphonic music generation by combining a Convolutional Restricted Boltzmann Machine with gradient descent constraint optimization and Simulated Annealing, resulting in the ability to impose self-similarity, meter, and tonal properties while maintaining local coherence.
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 optimisation 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 the newly generated material. The sampling process is guided with Simulated Annealing to avoid local optima, and to 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, and the tonal properties of the resulting musical piece, while preserving its local musical coherence.