SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

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 stud

Read original source ↗ Open in workspace

recordType

paper

region

Global