פיצ'-קלאס סטירינג לשיפור דיפוזיה-בייסד מוזיקה תורן

תקציר מקורי באנגליתarXiv:2609.04516v1 Announce Type: cross Abstract: 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 with respect to the denoising latent is used to nudge generation toward a user-specified pitch-class sequence, requiring no retraining or architectural