Metraipolis › archive › dc_ca6ffa2afd35

Auditing Bias and Safety in Voice AI Customer Care — arXiv:2609.04206

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.04206
License (as archived): CC0-1.0
Archived: 2026-10-16T22:35:41.874Z
SHA-256 of the archived text: 2c6065fa22447a7da6ea08dc4455b71f10ca3e90728d4fe4b846fe85d731e30c
Stable URL of this page: https://metraipolis.com/documento/dc_ca6ffa2afd35

How to cite

Auditing Bias and Safety in Voice AI Customer Care — arXiv:2609.04206 — arXiv (en), https://arxiv.org/abs/2609.04206 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca6ffa2afd35 (Metraipolis archive dc_ca6ffa2afd35, sha256 2c6065fa22447a7da6ea08dc4455b71f10ca3e90728d4fe4b846fe85d731e30c)

BibTeX

@misc{dcca6ffa2afd35,
  title = {Auditing Bias and Safety in Voice AI Customer Care — arXiv:2609.04206},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04206},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca6ffa2afd35; sha256 2c6065fa22447a7da6ea08dc4455b71f10ca3e90728d4fe4b846fe85d731e30c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04206. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Voice AI systems increasingly mediate customer care interactions where caller presentation cues such as accent, affect, fluency, and urgency are available alongside the service request. Existing fairness and safety evaluations cover speech recognition disparities, spoken dialogue bias, and voice agent capability, but rarely treat customer care voice agents as stateful, multi turn, tool mediated systems where harm can appear as additional burden before any final denial occurs. We formalize a validation gated audit framework for such systems. The framework (i) separates native speech to speech, cascaded ASR to language model to TTS, and hybrid tool mediated architectures; (ii) uses matched service facts across controlled caller presentation conditions; (iii) validates fact invariance, presentation cues, artifacts, and acoustic measurements before inference; and (iv) records both material outcomes and path to service burden. We define the research problem, methodology, seven validation gates, a six family metric set, and claim boundaries for an active industry evaluation program. We illustrate the framework with a fully synthetic worked example of a refund dispute audit instance. Production system results are excluded from this release; public reporting is gated by the validation protocol.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CL).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Computation and Language (cs.CL); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.04206 — 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 2026-10-16T22:21:16.306Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).