analiza aiqbench
This research addresses a critical bottleneck in Retrieval-Augmented Generation (RAG) for audio by introducing "relational synthesis," which prevents model leakage while maintaining acoustic fidelity. By leveraging structural costs to reorganize source grains based on reference temporal dynamics, the method effectively balances Foley production goals with neural generation constraints. This advancement represents a significant step toward scalable, high-quality synthetic audio systems that integrate seamlessly with existing retrieval architectures.
Relational Synthesis: Structure-Mediated Concatenative Synthesis for Foley and Retrieval-Augmented Audio Generation
arXiv:2610.05768v1 Announce Type: cross Abstract: We ask: given a retrieved source audio $S$ and a separate reference audio $R$, can we synthesize novel audio $Y$ out of this pair $(S,R)$ such that $Y$ remains acoustically consistent with $S$, while not persistently copying segments of $S$ or $R$? The first clause is a well-known goal in Foley audio production, and the second is a well-known issue in neural RAG when $S$ and $R$ are naively injected into neural generators. We show that both clauses can be addressed simultaneously using a method we coin relational synthesis, a variation of concatenative synthesis where target cost is replaced by a relational Gromov-like structural cost. Rather than imitating the content of $R$, relational synthesis exploits it from the "other side of the hill": it transfers the temporal structure and directed amplitude motion of $R$ to reorganize and concatenate the grains of $S$ in a novel manner that protects $S$'s acoustic information. Our experiments show that relational synthesis integrates naturally with neural RAG and produces Foley audio that performs well on metrics measuring temporal agreement, acoustic fidelity, and leakage persistence, while maintaining distribution-level quality and text alignment.
Abstract:We ask: given a retrieved source audio $S$ and a separate reference audio $R$, can we synthesize novel audio $Y$ out of this pair $(S,R)$ such that $Y$ remains acoustically consistent with $S$, while not persistently copying segments of $S$ or $R$? The first clause is a well-known goal in Foley audio production, and the second is a well-known issue in neural RAG when $S$ and $R$ are naively injected into neural generators. We show that both clauses can be addressed simultaneously using a method we coin relational synthesis, a variation of concatenative synthesis where target cost is replaced by a relational Gromov-like structural cost. Rather than imitating the content of $R$, relational synthesis exploits it from the "other side of the hill": it transfers the temporal structure and directed amplitude motion of $R$ to reorganize and concatenate the grains of $S$ in a novel manner that protects $S$'s acoustic information. Our experiments show that relational synthesis integrates naturally with neural RAG and produces Foley audio that performs well on metrics measuring temporal agreement, acoustic fidelity, and leakage persistence, while maintaining distribution-level quality and text alignment.
5 pages, 2 figures, 1 table. Submitted to ICASSP 2027. Audio demo: this https URL. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
Sound (cs.SD); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS)
arXiv:2610.05768 [cs.SD]
(or arXiv:2610.05768v1 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2610.05768 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 255 cuvinte
Subiecte conexe
Does preservation make sense before we know how to revive?
LessWrong · 15 iun. 2026
XtalPi Holdings Limited: XtalPi Holdings Announces 2026 Interim Results
finanznachrichten.de · 19 aug. 2026
A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation
arXiv · 17 iun. 2026
Scaling Karpathy’s LLM wiki: Why your knowledge base needs a graph
Neo4j · 31 aug. 2026