English

Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation

Sound 2022-07-29 v2 Artificial Intelligence Machine Learning Audio and Speech Processing

Abstract

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.

Keywords

Cite

@article{arxiv.2205.03043,
  title  = {Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation},
  author = {Zui Chen and Yansen Jing and Shengcheng Yuan and Yifei Xu and Jian Wu and Hang Zhao},
  journal= {arXiv preprint arXiv:2205.03043},
  year   = {2022}
}

Comments

8 pages, 8 figures. v2: IJCAI2022 published, format revisions and bugfixes

R2 v1 2026-06-24T11:08:59.619Z