Metraipolis › archive › dc_d5578bd901ec

TAG-Bench: Benchmarking Temporal Audio Grounding in Large Audio Language Models — arXiv:2609.01542

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01542
License (as archived)
CC0-1.0
Archived
2026-10-17T07:34:11.100Z
SHA-256 of the archived text
ee59a6e11a11109f3850b599650af8d95272f6c7fb75b71a26c80466ba71764a
Stable URL of this page
https://metraipolis.com/documento/dc_d5578bd901ec

How to cite

TAG-Bench: Benchmarking Temporal Audio Grounding in Large Audio Language Models — arXiv:2609.01542 — arXiv (en), https://arxiv.org/abs/2609.01542 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d5578bd901ec (Metraipolis archive dc_d5578bd901ec, sha256 ee59a6e11a11109f3850b599650af8d95272f6c7fb75b71a26c80466ba71764a)
BibTeX
@misc{dcd5578bd901ec,
  title = {TAG-Bench: Benchmarking Temporal Audio Grounding in Large Audio Language Models — arXiv:2609.01542},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01542},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d5578bd901ec; sha256 ee59a6e11a11109f3850b599650af8d95272f6c7fb75b71a26c80466ba71764a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01542. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large audio language models (LALMs) can describe what is heard, but their ability to localize when queried content occurs remains less systematically evaluated. We present TAG-Bench, a benchmark for temporal audio grounding in which a model returns every time interval that matches a natural-language query. TAG-Bench contains 1,750 human-verified query-recording pairs covering 149.5 hours, with eight source-dependent subsets spanning query categories and audio durations from 7 s to 20 min; 22.1% of the queries have multiple ground-truth intervals. Across 21 evaluated systems, the best-performing model achieves 31.2 mIoU and is the only system above 20 mIoU on the two long subsets, yet even this top performer reaches only 21.5% recall at IoU >= 0.7. Moreover, 9 of 21 systems fall below 5 mIoU, and every model under-reports the number of occurrences on one-to-many queries, with none exceeding 13.2% count accuracy. Because responses are free-form, we report parsing-failure rate and MAE coverage: parsing failures remain in mIoU, Recall, gIoU, and count metrics as empty predictions but do not enter MAE. The results separate precise localization, occurrence enumeration, and output-format reliability within a benchmark whose cross-subset comparisons are descriptive rather than controlled estimates of query abstraction or duration. We will release the TAG-Bench data and evaluation code to support future research.

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/2609.01542 — 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 2026-10-17T07:27:11.530Z 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).