Metraipolis › archive › dc_5e3ef4e96f72
Relational Synthesis: Structure-Mediated Concatenative Synthesis for Foley and Retrieval-Augmented Audio Generation — arXiv:2610.05768
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05768
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:27:09.794Z
- SHA-256 of the archived text
32c5799252ad730fc675881fa5c9deb21a432153a407d796b954591a07a55aa9- Stable URL of this page
https://metraipolis.com/documento/dc_5e3ef4e96f72
How to cite
Relational Synthesis: Structure-Mediated Concatenative Synthesis for Foley and Retrieval-Augmented Audio Generation — arXiv:2610.05768 — arXiv, https://arxiv.org/abs/2610.05768 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5e3ef4e96f72 (Metraipolis archive dc_5e3ef4e96f72, sha256 32c5799252ad730fc675881fa5c9deb21a432153a407d796b954591a07a55aa9)
BibTeX
@misc{dc5e3ef4e96f72,
title = {Relational Synthesis: Structure-Mediated Concatenative Synthesis for Foley and Retrieval-Augmented Audio Generation — arXiv:2610.05768},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05768},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5e3ef4e96f72; sha256 32c5799252ad730fc675881fa5c9deb21a432153a407d796b954591a07a55aa9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05768. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2610.05768 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:24:06.069Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).