用图神经网络模拟频移合成信号流，实现音色到音色预设的精准检索。
FM Synthesizer Audio-Parameter Shared Embeddings
- 设计图神经网络模拟FM合成器信号路由，参数共享提升泛化能力。
- 在32种拓扑中训练后，对未见拓扑仍保持高检索准确率。
- 适合音色设计、音频生成与音乐人工智能研究者参考。
给定目标音色，找到能最佳重现它的合成器预设仍是声音设计中的核心问题。现有方法将合成参数视为平坦向量，忽略了产生音频的信号路由和参数交互。本文提出两项贡献：首先，为学习包含信号路由的参数表示，设计了消息传递结构模仿FM信号处理的图神经网络；其次，借鉴SLAP的多模态目标，学习音频与FM合成器参数的联合嵌入，实现从预设库中检索。聚焦Yamaha DX7，其六组相同的正弦波运算器根据32种拓扑之一相互作用。图编码器的消息传递权重在所有节点和层间共享，可处理任意规模的拓扑。当所有拓扑均参与训练时，DX7-GNN与两个基线在音色到预设检索任务上表现良好；当部分拓扑留出测试时，尽管参数最少，DX7-GNN显著优于两个基线。消融实验进一步支持：在参数编码器中模仿FM信号流有助于提升对未见拓扑的泛化能力。
原文摘要 · Abstract (English)
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.
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。