Coupled Recurrent Models For Polyphonic Music Composition

Abstract

This paper introduces a novel recurrent model for music composition that is tailored to the structure of polyphonic music. We propose an efficient new conditional probabilistic factorization of musical scores, viewing a score as a collection of concurrent, coupled sequences: i.e. voices. To model the conditional distributions, we borrow ideas from both convolutional and recurrent neural models; we argue that these ideas are natural for capturing music's pitch invariances, temporal structure, and polyphony. We train models for single-voice and multi-voice composition on 2,300 scores from the KernScores dataset.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keythickstun2018coupled

Related papers

• Rethinking Recurrent Latent Variable Model For Music Composition (2018)7.50
• A Holistic Approach To Polyphonic Music Transcription With Neural Networks (2019)0.00
• Multi-modal Conditional Bounding Box Regression For Music Score Following (2021)5.24
• A Predictive Model For Music Based On Learned Interval Representations (2018)0.00
• Polyphonic Music Generation With Sequence Generative Adversarial Networks (2017)2.26
• Imposing Higher-level Structure In Polyphonic Music Generation Using Convolutional Restricted Boltzmann Machines And Constraints (2016)6.77
• Modeling Music Modality With A Key-class Invariant Pitch Chroma CNN (2019)0.00
• Bandcondinet: Parallel Transformers-based Conditional Popular Music Generation With Multi-view Features (2024)0.00