AI 中文总结
针对合成器预设检索问题，本文设计模仿FM信号处理的图神经网络学习含信号路由的参数表征，结合SLAP多模态目标学习音频与FM合成器参数的联合嵌入，在Yamaha DX7数据集上验证了方法的有效性与泛化性。
AI 中文摘要
给定目标声音，找到能最佳复现它的合成器预设仍是声音设计的核心问题。现有方法将合成参数视为扁平向量，忽略了产生音频的信号路由与参数间的相互作用。我们做出两项贡献：第一，为学习包含信号路由的参数表征，我们设计了一种图神经网络，其消息传递结构模仿FM信号处理；第二，我们将来自SLAP的多模态目标进行适配，以学习音频与FM合成器参数的联合嵌入，从而支持从图库中检索预设。我们以Yamaha DX7为研究对象，其中六个相同的正弦算子会根据32种路由拓扑结构之一进行交互。我们的图编码器的消息传递权重在所有节点和层间共享，可处理任意大小的任意拓扑结构。当训练过程中看到所有拓扑结构时，DX7-GNN与两个基线方法均实现了出色的音频到预设检索性能。当部分拓扑结构被留出用于测试时，尽管DX7-GNN的参数最少，其性能仍显著优于两个基线方法。我们的 ablation 实验进一步支持以下结论：在参数编码器中模仿FM信号流可提升对未见过的拓扑结构的泛化能力。
英文摘要
Given a target sound, finding the synthesizer preset that best reproduces it remains a core problem in sound design. Existing methods treat synthesis parameters as flat vectors, discarding the signal routing and parameter interactions that produce audio. We make two contributions. First, to learn a representation of parameters including their signal routing, we design a graph neural network whose message passing structure imitates FM signal processing. Second, we adapt the multimodal objective from SLAP to learn joint embeddings of audio and FM synthesizer parameters, enabling preset retrieval from a gallery. We focus on the Yamaha DX7, where six identical sinusoid operators interact according to one of 32 routing topologies. Our graph encoder's message passing weights are shared across all nodes and layers, enabling processing of arbitrary topologies of any size. When every topology is seen during training, the DX7-GNN and two baselines achieve strong audio-to-preset retrieval. When some topologies are held out for testing, the DX7-GNN substantially outperforms both baselines despite having the fewest parameters. Our ablations further support the claim that imitating FM signal flow in a parameter encoder improves generalization to unseen topologies.
CommentsAccepted to DAFx 2026
