Coupled Recurrent Models for Polyphonic Music Composition
This addresses the problem of generating structured polyphonic music for composers and AI researchers, but it appears incremental as it builds on existing neural models.
The paper tackles polyphonic music composition by proposing a novel recurrent model that views scores as coupled sequences of voices, achieving training on 2,300 scores from the KernScores dataset.
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.