Performance Conditioning for Diffusion-Based Multi-Instrument Music Synthesis
This addresses a central unsolved issue in Music Information Retrieval for generating musically and acoustically controlled multi-instrument music, though it appears incremental as it builds on existing diffusion models.
The paper tackles the problem of controlling timbre and style in multi-instrument music synthesis from symbolic representations by conditioning a diffusion-based generative model on specific performances and recording environments, achieving state-of-the-art FAD realism scores.
Generating multi-instrument music from symbolic music representations is an important task in Music Information Retrieval (MIR). A central but still largely unsolved problem in this context is musically and acoustically informed control in the generation process. As the main contribution of this work, we propose enhancing control of multi-instrument synthesis by conditioning a generative model on a specific performance and recording environment, thus allowing for better guidance of timbre and style. Building on state-of-the-art diffusion-based music generative models, we introduce performance conditioning - a simple tool indicating the generative model to synthesize music with style and timbre of specific instruments taken from specific performances. Our prototype is evaluated using uncurated performances with diverse instrumentation and achieves state-of-the-art FAD realism scores while allowing novel timbre and style control. Our project page, including samples and demonstrations, is available at benadar293.github.io/midipm