# ST-ITO: Controlling Audio Effects for Style Transfer with Inference-Time Optimization

arXiv: https://arxiv.org/abs/2410.21233 · HTML: https://mlsanity.com/paper/2410.21233/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2024.

## Built on by (most cited first, 7 of 7)

- [Unsupervised Estimation of Nonlinear Audio Effects: Comparing Diffusion-Based and Adversarial approaches](https://mlsanity.com/paper/2504.04751/) (2025)
- [Improving Inference-Time Optimisation for Vocal Effects Style Transfer with a Gaussian Prior](https://mlsanity.com/paper/2505.11315/) (2025)
- [WildFX: A DAW-Powered Pipeline for In-the-Wild Audio FX Graph Modeling](https://mlsanity.com/paper/2507.10534/) (2025)
- [TimberAgent: Gram-Guided Retrieval for Executable Music Effect Control](https://mlsanity.com/paper/2603.09332/) (2026)
- [Decomposer: Learning to Decompile Symbolic Music to Programs](https://mlsanity.com/paper/2607.01849/) (2026)
- [Music Restoration via Latent Operator Optimization and Diffusion Model Priors](https://mlsanity.com/paper/2608.01972/) (2026)
- [Diff2Mix: Controllable Music Mixing via Diffusion Models and Differentiable Audio Effects](https://mlsanity.com/paper/2608.05442/) (2026)

## Abstract (arXiv)

Audio production style transfer is the task of processing an input to impart stylistic elements from a reference recording. Existing approaches often train a neural network to estimate control parameters for a set of audio effects. However, these approaches are limited in that they can only control a fixed set of effects, where the effects must be differentiable or otherwise employ specialized training techniques. In this work, we introduce ST-ITO, Style Transfer with Inference-Time Optimization, an approach that instead searches the parameter space of an audio effect chain at inference. This method enables control of arbitrary audio effect chains, including unseen and non-differentiable effects. Our approach employs a learned metric of audio production style, which we train through a simple and scalable self-supervised pretraining strategy, along with a gradient-free optimizer. Due to the limited existing evaluation methods for audio production style transfer, we introduce a multi-part benchmark to evaluate audio production style metrics and style transfer systems. This evaluation demonstrates that our audio representation better captures attributes related to audio production and enables expressive style transfer via control of arbitrary audio effects.