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

Abstract:Procedural audio has emerged as a viable source for transferable audio representation learning, but its design principles remain this http URL revisit two questions: how a procedural source should be scaled, and whether training choices developed on natural audio should transfer unchanged to procedural this http URL a controlled source, we separate scale into formula-class coverage C and within-class rendering diversity this http URL 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 this http URL is available at this https URL.

Sound (cs.SD); Artificial Intelligence (cs.AI)

arXiv:2609.15067 [cs.SD]

(or arXiv:2609.15067v1 [cs.SD] for this version)

https://doi.org/10.48550/arXiv.2609.15067 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.