RedVox：語音模型在不同語言間的安全性與公平性差距

摘要

具備語音能力的模型越來越多地被部署於跨語言的現實應用中，然而，其在英語環境之外及自然情境下的安全性與公平性仍研究不足。我們調查了最先進語音模型發布中的安全報告實務，發現僅有8%的文件包含了多語言分析。為填補此缺口，我們推出了RedVox，一個基於真實語音的多語言音訊與語音安全性及公平性基準測試，涵蓋五種語言（英語、法語、義大利語、西班牙語及德語）中不安全與不公平的刻板請求。透過評估八個最先進模型，我們發現即使在非對抗性條件下，漏洞依然存在；在非英語語言中情況更為惡化，且當請求來自語音輸入時，此漏洞會被放大。最後，透過調查貢獻RedVox的參與者，我們記錄了在招募人類受試者收集語音資料時所面臨的獨特個人與隱私挑戰，進而指出自然語音安全研究中更廣泛的社會技術挑戰。

English

Speech-capable models are increasingly deployed in real-world applications across languages. Yet their safety and fairness beyond English settings and under naturalistic conditions remain understudied. We survey safety reporting practices across state-of-the-art speech model releases, finding that only 8% document any multilingual analysis. To address this gap, we introduce RedVox, a multilingual safety and fairness benchmark for audio and speech built on real voices, covering unsafe and unfair stereotypical requests across five languages (English, French, Italian, Spanish, and German). Evaluating eight state-of-the-art models, we find that vulnerabilities persist even under non-adversarial conditions, worsen in non-English languages, and are amplified when the request comes from a spoken input. Finally, by surveying the participants who contributed to RedVox, we document the unique personal and privacy challenges of collecting speech data with human participants, pointing to broader sociotechnical challenges in naturalistic speech safety research.