Rethinking Procedural Audio Pre-training: Source Scaling and Objective Adaptation

2026-09-14

AI Summary

研究探讨了过程音频的缩放原则及训练选择，通过控制源分离缩放类型，使用FDSL和AudioMAE实验，提出应根据源特性调整预训练策略。

Abstract

Procedural audio has emerged as a viable source for transferable audio representation learning, but its design principles remain unclear.We revisit two questions: how a procedural source should be scaled, and whether training choices developed on natural audio should transfer unchanged to procedural data.Using a controlled source, we separate scale into formula-class coverage C and within-class rendering diversity I.Experiments with FDSL and AudioMAE show that these two forms of scale provide different benefits and depend on the learning formulation and downstream task. A matched AudioMAE study further shows that procedural audio favors low mask ratios (10%--25%), whereas AudioSet-28K favors 50%--75%. Shared-codebook analysis reveals lower patch diversity and stronger temporal predictability in procedural audio. These results motivate source-aware procedural pre-training, where source scaling and learning configuration are considered jointly.Code is available at https://github.com/Cross-Innovation-Lab/Formula-Bank.

Problem

• Procedural Audio
• Pre-training
• Source Scaling
• Objective Adaptation
• Transfer Learning

Innovation

• Procedural Audio
• Source Scaling
• Objective Adaptation
• Mask Ratios
• Temporal Predictability