SOURCE-LINKED INTELLIGENCE

Evaluating Loss Functions in Differentiable Out-of-Domain Sound-Matching with Partial Parameter Distance

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

In out-of-domain (OOD) sound-matching, a synthesizer is optimized to mimic a sound it did not generate. OOD evaluation of loss functions is underexplored in part because the standard "parameter loss" metric requires a shared parameter space between target and imitator, which OOD settings lack. We introduce Partial Parameter Distance (PPD), which applies parameter loss only to the critical parameters that mismatched synthesizers share (e.g., filter cutoffs), enabling automatically evaluated OOD experiments; we verify its results with blinded listening tests. Across seven scenarios involving ban

Read original source ↗ Open in workspace

recordType

paper

region

Global