提出空间音频评估新框架，验证不同指标对方位变化的敏感度。
Sensitivity Analysis of Generative Spatial Audio Metrics: A Study on Responsiveness, Smoothness, and Symmetry
- 基于参数化声音合成思路，构建沿连续轨迹的敏感度分析框架。
- 定位专用嵌入+声学图的FAD在复杂场景下仍保持高响应性与平滑性。
- 强度向量随场景复杂度增加而性能下降，不适用于复杂空间音频评估。
生成式一阶全向音频（FOA）的评估仍具挑战性，因缺乏对度量指标如何响应方位角和仰角等空间参数变化的理解。本文提出一种框架，用于分析指标在连续空间轨迹上的敏感度，借鉴了参数化声音合成中的敏感度分析原理。通过控制复杂度递增的FOA场景，定义了三个理想指标行为：响应性、平滑性和对称性。评估了标准的分布基与样本基度量，包括音频弗雷谢距离（FAD）、强度向量和声学图。结果表明，在不同条件下，使用定位专用嵌入的FAD与声学图表现出高响应性及稳健的平滑性和对称性；而强度向量在场景复杂度增加时性能显著下降。这是迈向生成式空间音频度量敏感性研究的第一步。
原文摘要 · Abstract (English)
Evaluating generative spatial audio for First-Order Ambisonics (FOA) remains challenging due to a limited understanding of how metrics respond to changes in spatial parameters such as azimuth and elevation. We propose a framework to analyze metric sensitivity along continuous spatial trajectories, drawing on principles of sensitivity analysis in parametric sound synthesis. Using controlled FOA scenes with increasing scene complexity, we define three desiderata for metric behavior: Responsiveness, Smoothness, and Symmetry. We assess standard distribution-based and sample-based metrics, including Fréchet Audio Distance (FAD), intensity vectors, and acoustic maps. Our findings show that FAD using localization-specific embeddings and acoustic maps yield high Responsiveness and robust Smoothness and Symmetry across conditions, while intensity vectors degrade with increasing scene complexity. This is the first step towards investigating the sensitivity of metrics for generative spatial audio.
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。