# Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation

arXiv: https://arxiv.org/abs/2205.03043 · HTML: https://mlsanity.com/paper/2205.03043/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 27 references that are in the map.
- First posted on arXiv 6 May 2022.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [DDSP: Differentiable Digital Signal Processing](https://mlsanity.com/paper/2001.04643/) (2020)
- [Universal audio synthesizer control with normalizing flows](https://mlsanity.com/paper/1907.00971/) (2019)
- [SerumRNN: Step by Step Audio VST Effect Programming](https://mlsanity.com/paper/2104.03876/) (2021)

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

- [DDX7: Differentiable FM Synthesis of Musical Instrument Sounds](https://mlsanity.com/paper/2208.06169/) (2022)
- [Synthesizer Preset Interpolation using Transformer Auto-Encoders](https://mlsanity.com/paper/2210.16984/) (2022)
- [Modulation Discovery with Differentiable Digital Signal Processing](https://mlsanity.com/paper/2510.06204/) (2025)
- [NAS-FM: Neural Architecture Search for Tunable and Interpretable Sound Synthesis based on Frequency Modulation](https://mlsanity.com/paper/2305.12868/) (2023)
- [Neural Proxies for Sound Synthesizers: Learning Perceptually Informed Preset Representations](https://mlsanity.com/paper/2509.07635/) (2025)
- [DDSynth-RL: Audio Synthesizer Inversion via Discrete Diffusion with Reinforcement Learning](https://mlsanity.com/paper/2608.03032/) (2026)
- [Off-manifold robustness in synthesizer inversion with joint distribution flow matching](https://mlsanity.com/paper/2609.29320/) (2026)

## Abstract (arXiv)

Synthesizer is a type of electronic musical instrument that is now widely used in modern music production and sound design. Each parameters configuration of a synthesizer produces a unique timbre and can be viewed as a unique instrument. The problem of estimating a set of parameters configuration that best restore a sound timbre is an important yet complicated problem, i.e.: the synthesizer parameters estimation problem. We proposed a multi-modal deep-learning-based pipeline Sound2Synth, together with a network structure Prime-Dilated Convolution (PDC) specially designed to solve this problem. Our method achieved not only SOTA but also the first real-world applicable results on Dexed synthesizer, a popular FM synthesizer.