Metraipolis › archive › dc_81044f3b9ffb
Voice-Native LLMs Hear Frustration but Do Not Listen to It — arXiv:2611.02893
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02893
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:20:14.307Z
- SHA-256 of the archived text
e399783bf6db95b850056091bbf2421457166d4663857d4323d2a3c05fc8d4c7- Stable URL of this page
https://metraipolis.com/documento/dc_81044f3b9ffb
How to cite
Voice-Native LLMs Hear Frustration but Do Not Listen to It — arXiv:2611.02893 — arXiv (en), https://arxiv.org/abs/2611.02893 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_81044f3b9ffb (Metraipolis archive dc_81044f3b9ffb, sha256 e399783bf6db95b850056091bbf2421457166d4663857d4323d2a3c05fc8d4c7)
BibTeX
@misc{dc81044f3b9ffb,
title = {Voice-Native LLMs Hear Frustration but Do Not Listen to It — arXiv:2611.02893},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02893},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_81044f3b9ffb; sha256 e399783bf6db95b850056091bbf2421457166d4663857d4323d2a3c05fc8d4c7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02893. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Users convey frustration in what they say and in how they say it, and voice-native models, which hear speech instead of an ASR transcript, can register both. Existing evaluations read unchanged performance as robustness without checking perception. Following Brunswik's lens model, we measure on identical audio whether frustration is expressed, perceived, and utilized. We cross frustrated wording with frustrated voice in a within-item 2x2 design over 353 tasks and release the 1,412 clips as VoxAffect. Across 8 models, outputs look robust, with no detectable vocal effect on accuracy for 7. With neutral wording, all 8 label the frustrated voice frustrated in at most 3.1% of clips, although 7 of them detect acted anger in 73-100% of clips and human listeners classify the voice correctly in 65.3% of judgments. Yet linear probes decode the frustrated voice from the audio encoders of the 2 open-weight models, with paired accuracy 0.67 and 0.69, and in proprietary models too the voice raises perceived frustration once the words agree. The models thus hear the frustrated voice but do not listen to it, whereas their invariance to frustrated wording, perceived in 40-75% of clips, is genuine robustness. Our work is openly accessible at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2611.02893 — 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 2026-11-03T18:09:53.724Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).