提出一套评估语音客服系统偏见与安全的审计框架，关注服务过程中的累积负担。
Auditing Bias and Safety in Voice AI Customer Care
- 区分纯语音、串接式与工具辅助三种架构，分层检测偏差
- 通过控制发音特征验证事实一致性，发现隐藏的流程负担
- 适合关注语音AI公平性与用户体验的工业界研究者
语音AI在客户服务中扮演日益重要的角色，用户口音、情绪、流利度和紧急程度等呈现线索与服务请求一同被处理。现有公平性与安全性评估多聚焦于语音识别差异、对话偏见和语音代理能力，却很少将客服语音代理视为具有状态、多轮交互、工具驱动的系统——伤害可能表现为服务前的额外负担，而非最终拒绝。本文提出一种验证门控审计框架：(i) 区分原生语音到语音、串接式ASR-语言模型-TTS与混合工具驱动架构；(ii) 在受控的用户呈现条件下使用匹配的服务事实；(iii) 在推理前验证事实不变性、呈现线索、伪影及声学测量；(iv) 记录实际结果与服务路径上的负担。定义了研究问题、方法、七道验证门、六类指标集，并划定活跃产业评估项目的边界。以退款争议的全合成案例说明框架应用。生产系统结果未公开，公共报告受限于验证协议。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。