Proceedings

SynthRL: Cross-domain Synthesizer Sound Matching via Reinforcement Learning

Wonchul Shin, Kyogu Lee

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. AI, Arts & Creativity. Pages 10162-10170.

https://doi.org/10.24963/ijcai.2025/1129

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

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.

Wonchul Shin, and Kyogu Lee. 2025. SynthRL: Cross-domain Synthesizer Sound Matching via Reinforcement Learning. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 10162–10170. https://doi.org/10.24963/ijcai.2025/1129
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards