发表机构
University of Alberta（阿尔伯塔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出部分参数距离（PPD）解决域外声音匹配的损失函数评估难题，在7种场景评估4种损失函数，验证PPD可作为诊断工具辅助损失函数选择。
AI 中文摘要
在域外（OOD）声音匹配任务中，需优化合成器以模仿其未生成的声音。损失函数的OOD评估研究不足，部分原因是标准“参数损失”指标要求目标与模仿者拥有共享参数空间，而OOD场景缺乏该条件。本文提出部分参数距离（PPD），仅将参数损失应用于不匹配合成器共享的关键参数（如滤波器截止频率），使OOD实验可自动评估；通过盲听测试验证其结果。在涉及带通滤波、幅度调制和音高弯曲的7种场景中，评估4种可微分损失函数（SIMSE_Spec、L1_Spec、JTFS、DTW_Envelope）。损失函数的有效性与合成方法紧密相关：SIMSE_Spec擅长滤波器截止频率恢复，DTW_Envelope擅长幅度调制恢复，JTFS擅长平滑音高轨迹。基于参数的评估在7种场景中的5种与盲听测试对排名最高的损失函数判断一致，证明其作为诊断工具的实用性。
英文摘要
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.
