提出新评估方法，精准判断声音合成中不同损失函数的优劣。
Evaluating Loss Functions in Differentiable Out-of-Domain Sound-Matching with Partial Parameter Distance
- 仅对共享关键参数使用距离度量，实现无域外声音匹配的自动评估。
- 四种损失函数在七种场景中表现各异，与听觉测试结果高度一致。
- 适合研究声音合成、音频生成与模型评估的学者使用。
在无域外（OOD）声音匹配任务中，需优化合成器以模仿其未生成的声音。传统参数损失因依赖共享参数空间而难以应用，限制了损失函数评估。本文提出部分参数距离（PPD），仅对匹配合成器共有的关键参数（如滤波器截止频率）计算损失，实现自动化的OOD实验；并通过盲听测试验证结果。在涉及带通滤波、幅度调制和音高弯曲的七种场景中，评估了四种可微损失函数（SIMSE_Spec、L1_Spec、JTFS、DTW_Envelope）。结果表明，损失函数效果紧密依赖于合成方式：SIMSE_Spec在滤波器截止恢复上最优，DTW_Envelope在幅度调制恢复上最佳，JTFS在平滑音高轨迹上表现更佳。基于参数的评估在五种场景中与听觉测试结果一致，证明其作为诊断工具的有效性。
原文摘要 · Abstract (English)
In out-of-domain (OOD) sound-matching, a synthesizer is optimized to mimic a sound it did not generate. OOD evaluation of loss functions is underexplored in part because the standard "parameter loss" metric requires a shared parameter space between target and imitator, which OOD settings lack. We introduce Partial Parameter Distance (PPD), which applies parameter loss only to the critical parameters that mismatched synthesizers share (e.g., filter cutoffs), enabling automatically evaluated OOD experiments; we verify its results with blinded listening tests. Across seven scenarios involving band-pass filtering, amplitude modulation, and pitch-bending, we evaluate four differentiable loss functions (SIMSE_Spec, L1_Spec, JTFS, DTW_Envelope). Loss-function effectiveness remains tightly coupled to the method of synthesis: SIMSE_Spec excels at filter-cutoff recovery, DTW_Envelope at amplitude-modulation recovery, and JTFS at smooth pitch trajectories. Parameter-based evaluation agrees with listening tests on the top-ranked loss function in five of seven scenarios, demonstrating its utility as a diagnostic tool.
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。