Metraipolis › archive › dc_d1c17deebfd5
Auditing generative audio calls for known-task audio-llm evaluation — arXiv:2608.27817
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27817
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T10:56:43.061Z
- SHA-256 of the archived text
10304170ee1ee42e6f1d3fa7f1981c377fb10338636419433dde3b2db32a58bd- Stable URL of this page
https://metraipolis.com/documento/dc_d1c17deebfd5
How to cite
Auditing generative audio calls for known-task audio-llm evaluation — arXiv:2608.27817 — arXiv (en), https://arxiv.org/abs/2608.27817 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d1c17deebfd5 (Metraipolis archive dc_d1c17deebfd5, sha256 10304170ee1ee42e6f1d3fa7f1981c377fb10338636419433dde3b2db32a58bd)
BibTeX
@misc{dcd1c17deebfd5,
title = {Auditing generative audio calls for known-task audio-llm evaluation — arXiv:2608.27817},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27817},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d1c17deebfd5; sha256 10304170ee1ee42e6f1d3fa7f1981c377fb10338636419433dde3b2db32a58bd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27817. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Speech and audio LLMs are evaluated by comparing waveform predictions with predictions from an automatic speech recognition (ASR) transcript. For fixed closed-set tasks, this conflates acoustic evidence with the need to invoke a generative audio model. We estimate incremental call value with matched selectors sharing pre-call evidence. Each policy may retain the transcript label, use a local encoder, or invoke a generative model; matched control removes generative actions but preserves pre-call evidence and development selection. On VocalSound, transcript-only accuracy is 0.296, while supervised CLAP and WavLM controls reach 0.850 and 0.854 without calls. Full selector reaches 0.925 at 12.5% calls versus 0.921 for matched No-call selector (difference 0.004; 95% CI [-0.025, 0.033]). Thus, results do not show a call gain after transcript and encoder evidence are available. Relevant quantity is incremental accuracy from allowing calls, not the waveform-transcript gap. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CL). Categorie arXiv: Sound (cs.SD) ; Computation and Language (cs.CL); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2608.27817 — 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 2026-10-17T10:47:33.158Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).