Title: Quality Audio Prototyping: a prototype system for unified sound retrieval and procedural generation

Original: arXiv:2606.00629v1 Announce Type: cross Abstract: Sound design workflows frequently oscillate between time-consuming library searches and the complexity of procedural synthesis, with practitioners typically relying on disconnected tools to address each challenge separately. This paper introduces Quality Audio Prototyping (QuAP), a working prototype that unifies content-based audio retrieval and procedural sound generation within a single interface, reducing the procedural distance between a narrative concept and its sonic realisation. QuAP integrates a similarity-based retrieval engine with real-time procedural audio models, complemented by a rule-based assistant that provides perceptually informed parameter guidance, offering definitions and recommendations derived from empirical optimisation rather than requiring prior synthesis knowledge. Preliminary evaluation confirms the viability of this approach: subjective assessment demonstrated statistically significant quality improvements in five of six embedded synthesis models, and an encoder ablation study established the preferred retrieval architecture on a sound effect dataset. A user evaluation with 16 practitioners confirmed the tool's workflow utility, with all participants agreeing that the parameter assistant preserved creative agency while lowering the barrier to procedural interaction.

Rewrite:

Sound design processes are often characterized by a disjointed back-and-forth between laborious library searches and the intricate demands of procedural synthesis, with creators typically employing separate, unconnected tools for each task. To bridge this gap, we present Quality Audio Prototyping (QuAP), a functional prototype that merges content-based audio retrieval with procedural sound generation into one cohesive interface. This integration significantly shortens the procedural gap between a narrative idea and its final auditory form.

QuAP combines a retrieval engine based on similarity matching with real-time procedural audio models. It is further supported by a rule-based assistant that offers guidance on parameters informed by human perception. This assistant delivers definitions and suggestions rooted in empirical optimization, eliminating the need for users to possess prior expertise in synthesis.

Initial assessments validate the effectiveness of this methodology. Subjective testing revealed statistically significant enhancements in the quality of five out of the six integrated synthesis models. Additionally, an ablation study of the encoder determined the optimal retrieval architecture using a sound effect dataset. A subsequent evaluation involving 16 industry practitioners highlighted the tool’s practical value in workflows. All participants noted that the parameter assistant maintained their creative control while simultaneously reducing the difficulty of engaging with procedural synthesis.

Source: arXiv Generated at: 2026-06-02 00:00:00 UTC