SOURCE-LINKED INTELLIGENCE

Pitch-class Steering for Diffusion-based Music Generation via Latent-space Probes

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Recent work on controllable music generation has focused on autoregressive models, leaving diffusion-based systems comparatively underexplored. We present a lightweight method for steering the pitch content of audio produced by Stable Audio Open, a latent diffusion model for music synthesis. A small convolutional probe containing approximately 125k parameters is trained to decode frame-level pitch-class activations from the model's variational autoencoder latent space, using paired audio and MIDI data. At inference time, the frozen probe serves as a differentiable loss function: its gradient w

Read original source ↗ Open in workspace

recordType

paper

region

Global