# Synthesizer Preset Interpolation using Transformer Auto-Encoders

arXiv: https://arxiv.org/abs/2210.16984 · HTML: https://mlsanity.com/paper/2210.16984/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 27 Oct 2022.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications](https://mlsanity.com/paper/1701.05517/) (2017)
- [Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders](https://mlsanity.com/paper/1704.01279/) (2017)
- [DDSP: Differentiable Digital Signal Processing](https://mlsanity.com/paper/2001.04643/) (2020)
- [Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer](https://mlsanity.com/paper/1807.07543/) (2018)
- [DDX7: Differentiable FM Synthesis of Musical Instrument Sounds](https://mlsanity.com/paper/2208.06169/) (2022)
- [InverSynth: Deep Estimation of Synthesizer Parameter Configurations from Audio Signals](https://mlsanity.com/paper/1812.06349/) (2018)
- [Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation](https://mlsanity.com/paper/2205.03043/) (2022)
- [SerumRNN: Step by Step Audio VST Effect Programming](https://mlsanity.com/paper/2104.03876/) (2021)
- [VaPar Synth -- A Variational Parametric Model for Audio Synthesis](https://mlsanity.com/paper/2004.00001/) (2020)

## Built on by (most cited first, 3 of 3)

- [SoundMorpher: Perceptually-Uniform Sound Morphing with Diffusion Model](https://mlsanity.com/paper/2410.02144/) (2024)
- [Neural Proxies for Sound Synthesizers: Learning Perceptually Informed Preset Representations](https://mlsanity.com/paper/2509.07635/) (2025)
- [Off-manifold robustness in synthesizer inversion with joint distribution flow matching](https://mlsanity.com/paper/2609.29320/) (2026)

## Abstract (arXiv)

Sound synthesizers are widespread in modern music production but they increasingly require expert skills to be mastered. This work focuses on interpolation between presets, i.e., sets of values of all sound synthesis parameters, to enable the intuitive creation of new sounds from existing ones. We introduce a bimodal auto-encoder neural network, which simultaneously processes presets using multi-head attention blocks, and audio using convolutions. This model has been tested on a popular frequency modulation synthesizer with more than one hundred parameters. Experiments have compared the model to related architectures and methods, and have demonstrated that it performs smoother interpolations. After training, the proposed model can be integrated into commercial synthesizers for live interpolation or sound design tasks.