Where to Perturb: Reference-Structured Corruption for One-Shot SFX Variation

One-shot SFX variation requires generating diverse yet recognizable alternatives from a single reference. Limited variability can lead to perceptual repetition in interactive media (e.g. video games), while manually designing variations is costly. Yet reference-guided flow models typically condition on the reference while applying a largely uniform corruption level across time, despite its heterogeneous acoustic structure. While recent asynchronous flow methods demonstrate that corruption can vary across a sequence, they do not specifically exploit the internal structure of an audio reference to allocate stochasticity for identity-preserving variation. We ask whether the internal structure of an audio latent can directly determine where and how strongly stochasticity should be introduced. We propose a Reference-Structured Corruption (RSC) that transforms a single reference into multiple stochastic trajectories without auxiliary conditioning or per-reference optimization. The method partitions the latent into content-aligned regions from latent geometry and activity, then assigns activity-conditioned regional flow times, yielding continuous control between preservation and regeneration. On Woosh, our method increases within-reference diversity from $1.29$ to $1.41$ WCIS while maintaining identity drift close to the level observed in real production SFX variations, and improves FAD from $4.82$ to $4.41$. On Stable Audio 3, it similarly increases WCIS from $1.69$ to $1.79$ while preserving generation quality ($6.39$ vs. $6.41$ FAD). These results show that the learned latent representation can serve not only as the generation space, but also as a signal for structuring the stochastic process itself. An anonymized, frozen demo page is available online. Code is included in the supplementary material and will be released publicly.