Sierra 发布 𝜏-i18n,将 𝜏-Voice 扩展到西班牙语、巴西葡萄牙语、印地语、韩语和普通话五种语言,沿用相同的航空、零售和电信任务、策略、工具与成功标准,以便跨语言比较。在 2,700 通主通话中,西班牙语、印地语、葡萄牙语的任务完成率平均落后英语 2.4、3.8、6.4 个百分点,韩语和普通话分别落后 22.6 和 9.1 个百分点,韩语是三个智能体中表现最弱的语言。除任务完成外,𝜏-i18n 还单独报告交互指标(响应时机、选择性、工具调用效率)和生成质量(自然度、语音保真度),并已开源代码库和语言包框架 LanguageFactory。
In our earlier 𝜏-Voice experiments, accents caused the largest average drop in task completion among the factors we tested. That raised a broader question: how well do voice agents work for callers in other languages? Today we’re introducing 𝜏-i18n (pronounced tau-internationalization), which extends 𝜏-Voice to five more languages: Spanish, Brazilian Portuguese, Hindi, Korean, and Mandarin. 𝜏-i18n uses the same airline, retail, and telecom tasks across languages. Tasks, policies, tools, and succ
匹配字段正文