用离散扩散模型和强化学习逆向合成器，让声音更精准匹配。
DDSynth-RL: Audio Synthesizer Inversion via Discrete Diffusion with Reinforcement Learning
- 用掩码离散扩散模型生成合成器参数，解决多参数对应同声音的问题。
- 经音频域奖励微调后，跨数据集声音匹配性能显著提升。
- 适合想精确控制合成音色的研究者或音乐创作工程师。
合成器逆向建模面临两大挑战：一是不同参数配置可能产生听觉上相似的声音；二是参数空间损失难以反映生成音频的相似性，且合成器作为不可微黑箱，难以直接进行音频域监督。为应对第一项挑战，本文将合成器逆向建模转化为离散参数上的条件生成任务，采用掩码离散扩散模型作为生成器，避免了自回归模型的固定顺序假设以及流匹配在类别控制变量上的连续松弛不匹配问题。为应对第二项挑战，进一步通过基于GRPO风格的音频域奖励对模型进行微调，该奖励由生成输出计算得出。在Dexed上的实验表明，经过监督训练后，离散扩散模型性能可媲美自回归与流匹配基线，而奖励微调进一步提升了跨领域音频匹配能力。代码与演示见：https://github.com/DDSynth-RL/DDSynthRL。
原文摘要 · Abstract (English)
Synthesizer inversion is challenging for two main reasons: 1) Distinct parameter configurations can produce perceptually similar sounds. 2) Parameter-space losses often fail to reflect rendered audio similarity, while the synthesizer being a non-differentiable black box prevents simple audio-domain supervision. To address the one-to-many mapping induced by the first challenge, we formulate synthesizer inversion as conditional generation over discrete synthesizer parameters and use masked discrete diffusion as the generator. This treatment additionally avoids the fixed-order assumption of autoregressive models and the continuous-relaxation mismatch of flow matching when modeling categorical synthesizer controls. To address the second challenge, we further fine-tune the model with GRPO-style audio-domain rewards computed from rendered outputs. Experiments on Dexed show that, after supervised training, the discrete diffusion model is competitive with autoregressive and flow-matching baselines, and reward-based fine-tuning further improves out-of-domain audio matching performance. Code and demos are available at: https://github.com/DDSynth-RL/DDSynthRL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。