Metraipolis › archive › dc_a9872b7fda3e

Ontology-based Target Sound Extraction — arXiv:2609.00752

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00752
License (as archived)
CC0-1.0
Archived
2026-10-17T07:34:11.093Z
SHA-256 of the archived text
5d0f14173570f19e29c11f8afcf73f4bd071ac97e599b9a6ac2c4362e045c02a
Stable URL of this page
https://metraipolis.com/documento/dc_a9872b7fda3e

How to cite

Ontology-based Target Sound Extraction — arXiv:2609.00752 — arXiv (en), https://arxiv.org/abs/2609.00752 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a9872b7fda3e (Metraipolis archive dc_a9872b7fda3e, sha256 5d0f14173570f19e29c11f8afcf73f4bd071ac97e599b9a6ac2c4362e045c02a)
BibTeX
@misc{dca9872b7fda3e,
  title = {Ontology-based Target Sound Extraction — arXiv:2609.00752},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00752},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a9872b7fda3e; sha256 5d0f14173570f19e29c11f8afcf73f4bd071ac97e599b9a6ac2c4362e045c02a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00752. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Target sound extraction (TSE) aims to isolate a sound source of interest from a mixture, given a semantic query. Existing TSE systems are conditioned on fixed class representations tied to individual sound categories, limiting their ability to handle the hierarchical relationships that naturally organize environmental sounds. In this paper, we introduce ontology-based TSE, a new task formulation in which a single model extracts sounds queried at any level of a sound ontology, from fine-grained leaf classes such as cat and dog to high-level categories such as animal. We propose a learnable class embedding table defined over all nodes of an AudioSet-derived ontology, regularized with a Cophenetic Correlation Coefficient (CPCC) loss that aligns embedding distances with shortest-path distances in the ontology tree. Our experiments across different approaches show the benefit of considering the ontology structure when training TSE systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in eess.AS).
Categorie arXiv: Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.00752 — 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 2026-10-17T07:27:11.529Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).