---
title: "SynthRL: Cross-domain Synthesizer Sound Matching via Reinforcement Learning"
authors:
  - "Wonchul Shin"
  - "Kyogu Lee"
doi: "10.24963/ijcai.2025/1129"
url: "https://ijcai.org/proceedings/2025/1129"
pdf: "https://ijcai.org/proceedings/2025/1129.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "10162-10170"
track: "AI, Arts & Creativity"
keywords:
  - "Methods and resources: Machine learning, deep learning, neural models, reinforcement learning"
  - "Application domains: Music and sound"
  - "Theory and philosophy of arts and creativity in AI systems: Autonomous creative or artistic AI"
---

# SynthRL: Cross-domain Synthesizer Sound Matching via Reinforcement Learning

Wonchul Shin, Kyogu Lee

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 10162-10170. DOI: [10.24963/ijcai.2025/1129](https://doi.org/10.24963/ijcai.2025/1129)

## Abstract

Generalization of synthesizer sound matching to external instrument sounds is highly challenging due to the non-differentiability of sound synthesis process which prohibits the use of out-of-domain sounds for training with synthesis parameter loss. We propose SynthRL, a novel reinforcement learning (RL)-based approach for cross-domain synthesizer sound matching. By incorporating sound similarity into the reward function, SynthRL effectively optimizes synthesis parameters without ground-truth labels, allowing fine-tuning on out-of-domain sounds. Furthermore, we introduce a transformer-based model architecture and reward-based prioritized experience replay to enhance RL training efficiency, considering the unique characteristics of the task. Experimental results demonstrate that SynthRL outperforms state-of-the-art methods on both in-domain and out-of-domain tasks. Further experimental analysis validates the effectiveness of our reward design, showing a strong correlation with human perception of sound similarity.