Metraipolis › archive › dc_95085b4355a9

Rel2Traj: Inter-Source Relation-Aware Trajectory Generation for Text-To-Spatial-Audio — arXiv:2611.01147

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01147
License (as archived)
CC0-1.0
Archived
2026-11-03T19:09:18.629Z
SHA-256 of the archived text
9a8eace70aa07c7c3c7fd4b906dcd13cf506332dd47ad587f8ff785e02f415a0
Stable URL of this page
https://metraipolis.com/documento/dc_95085b4355a9

How to cite

Rel2Traj: Inter-Source Relation-Aware Trajectory Generation for Text-To-Spatial-Audio — arXiv:2611.01147 — arXiv (en), https://arxiv.org/abs/2611.01147 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_95085b4355a9 (Metraipolis archive dc_95085b4355a9, sha256 9a8eace70aa07c7c3c7fd4b906dcd13cf506332dd47ad587f8ff785e02f415a0)
BibTeX
@misc{dc95085b4355a9,
  title = {Rel2Traj: Inter-Source Relation-Aware Trajectory Generation for Text-To-Spatial-Audio — arXiv:2611.01147},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01147},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_95085b4355a9; sha256 9a8eace70aa07c7c3c7fd4b906dcd13cf506332dd47ad587f8ff785e02f415a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01147. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

"A car drives from front left to front right while a dog follows it." Such a description specifies no particular trajectory, yet imposes a constraint on the joint motion of both sources that must hold at every frame. Existing text-to-spatial-audio methods can position and move each sound source according to its description, but none of them ensures or verifies that such inter-source relations hold. We therefore propose Rel2Traj, which parses the description into sources, relations, and anchors, jointly generates the trajectories of all sources using a relation-conditioned diffusion model, and finally renders sounds from a pretrained text-to-audio model along these trajectories to produce binaural audio. For training and evaluation, we construct a synthetic dataset from a controlled language of source motions and inter-source relations. A single frame-wise relational geometry defines both our evaluation metric, the Relation Satisfaction Rate (RSR), and an auxiliary training loss. On motion-relation combinations held out from training, Rel2Traj maintains all relation types, whereas every baseline fails on at least one. A listening test further confirms that listeners recognize the described relations. To our knowledge, this is the first text-to-spatial-audio work to model relations among moving sources as explicit geometric constraints.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno).
Categorie arXiv: Sound (cs.SD) ; Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2611.01147 — 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 2026-11-03T18:26:07.773Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).