Imposing Higher-level Structure In Polyphonic Music Generation Using Convolutional Restricted Boltzmann Machines And Constraints

Abstract

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.

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keylattner2016imposing

Related papers

• Polyphonic Music Generation With Sequence Generative Adversarial Networks (2017)2.26
• Symphonygen: 3D Hierarchical Orchestral Generation With Controllable Harmony Skeleton (2026)0.00
• The Effect Of Explicit Structure Encoding Of Deep Neural Networks For Symbolic Music Generation (2018)11.49
• Rethinking Recurrent Latent Variable Model For Music Composition (2018)7.50
• Of All Stripes: Investigating Structure-informed Positional Encoding For Efficient Music Generation (2025)0.00
• Coupled Recurrent Models For Polyphonic Music Composition (2018)0.00
• Amadeus: Autoregressive Model With Bidirectional Attribute Modelling For Symbolic Music (2025)0.00
• Interactive Music Generation With Positional Constraints Using Anticipation-rnns (2017)0.00