# Style Transfer for Non-differentiable Audio Effects

arXiv: https://arxiv.org/abs/2309.17125 · HTML: https://mlsanity.com/paper/2309.17125/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 29 Sep 2023.

## Builds on (most cited first, 8 of 8)

- [Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing](https://mlsanity.com/paper/1903.10145/) (2019)
- [DDSP: Differentiable Digital Signal Processing](https://mlsanity.com/paper/2001.04643/) (2020)
- [Deep Voice: Real-time Neural Text-to-Speech](https://mlsanity.com/paper/1702.07825/) (2017)
- [Deep Learning for Tube Amplifier Emulation](https://mlsanity.com/paper/1811.00334/) (2018)
- [Style Transfer of Audio Effects with Differentiable Signal Processing](https://mlsanity.com/paper/2207.08759/) (2022)
- [Lightweight and interpretable neural modeling of an audio distortion effect using hyperconditioned differentiable biquads](https://mlsanity.com/paper/2103.08709/) (2021)
- [Differentiable Signal Processing With Black-Box Audio Effects](https://mlsanity.com/paper/2105.04752/) (2021)
- [A Feature Learning Siamese Model for Intelligent Control of the Dynamic Range Compressor](https://mlsanity.com/paper/1905.01022/) (2019)

## Abstract (arXiv)

Digital audio effects are widely used by audio engineers to alter the acoustic and temporal qualities of audio data. However, these effects can have a large number of parameters which can make them difficult to learn for beginners and hamper creativity for professionals. Recently, there have been a number of efforts to employ progress in deep learning to acquire the low-level parameter configurations of audio effects by minimising an objective function between an input and reference track, commonly referred to as style transfer. However, current approaches use inflexible black-box techniques or require that the effects under consideration are implemented in an auto-differentiation framework. In this work, we propose a deep learning approach to audio production style matching which can be used with effects implemented in some of the most widely used frameworks, requiring only that the parameters under consideration have a continuous domain. Further, our method includes style matching for various classes of effects, many of which are difficult or impossible to be approximated closely using differentiable functions. We show that our audio embedding approach creates logical encodings of timbral information, which can be used for a number of downstream tasks. Further, we perform a listening test which demonstrates that our approach is able to convincingly style match a multi-band compressor effect.