模型实际看到了什么？数据驱动的房间声学参数预测中的评估协议和输入可用性
What does the model actually see? Evaluation protocols and input availability in data-driven prediction of room acoustic parameters
浏览论文内容
中文总结 AI 辅助
研究数据驱动的房间声学参数预测中模型准确率与评估协议及输入可用性的关系，通过多条件测量活动评估三个模型家族，发现评估协议对准确率影响大，学习模型在声强和混响时间有优势，原始管道高精度在条件插值中重现。
中文摘要 AI 辅助
机器学习模型越来越多地用于从稀疏测量中预测ISO 3382-1房间声学参数，报告的决定系数通常高于0.85。本文表明这些数字往往由评估协议而非模型决定。通过在264座会议厅和180座音乐厅的多条件测量活动，在析因协议消融下评估了三个模型家族。基于行的分割和测试时测量的输入能重现高准确率；按位置分组并限制输入会降低准确率。以目标自身脉冲响应为输入评估的混合CNN将其用作位置指纹而非可转移声学信息。在部署一致的协议下，固定模型在不同协议间的差异比不同模型间的差异大一个数量级。学习模型在声强和混响时间方面仍有真正优势，原始管道的高精度在测量位置的条件插值中重新出现。
英文摘要
Machine-learnt models are increasingly used to predict ISO 3382-1 room acoustic parameters at unmeasured seats from sparse measurements, with reported coefficients of determination frequently above 0.85. This paper shows that such figures are often determined by the evaluation protocol rather than by the model. Using a multi-condition measurement campaign in a 264-seat conference hall and a 180-seat concert hall, three model families were evaluated under a factorial protocol ablation: validation splits either row-based or grouped by receiver position, and inputs either including measured-at-test quantities (the target position's impulse response, co-located parameter measurements, position identifiers) or restricted to source-receiver geometry and environmental state. Row-based splits with measured-at-test inputs reproduce the high reported accuracies (mean R^2 of 0.81 for the core parameters); grouped splits with deployment-consistent inputs reduce these to 0.09-0.60 and reorder the apparent difficulty of parameter classes. Access to the target's own impulse response at test time reproduces the high accuracy of the row-based folds but provides no benefit under grouped folds. The row-based figure reflects condition interpolation at the measured positions rather than transferable acoustic information. Under the deployment-consistent protocol the spread between Random Forest, the hybrid network, and inverse-distance weighting is several times smaller than the spread between protocols for a fixed model; the learnt models retain a measurable advantage for sound strength and reverberation time, and the high accuracy of the original pipelines re-emerges as condition interpolation at measured positions, a distinct and operationally useful task. A reporting checklist operationalises the findings.
发表机构
- Acoustics Laboratory (VAL), Alanya Alaaddin Keykubat University, 07425, Antalya, T\" u rkiye aff2 Department of Mechanical Engineering, Alanya Alaaddin Keykubat University, 07425, Antalya, T\" u rkiye
机构由 AI 辅助整理，请以论文原文为准。
