打造可快速测试多种对话角色的实时交互平台
PersonaKit (PK): A Plug-and-Play Platform for User Testing Diverse Roles in Full-Duplex Dialogue
- 通过JSON配置定义角色与打断行为策略
- 支持8种角色的A/B对比测试，验证策略有效性
- 适合研究对话角色一致性与社会语言行为的学者
随着语音对话系统从传统助手角色扩展至包括权威导师、不合作商户、分心员工等多样人格，其需具备符合角色的人类化对话轮换行为以维持心理沉浸感。然而，现有全双工系统常采用僵化的‘始终让步’策略，在重叠语音时严重破坏非顺从角色的一致性。通过真实用户研究评估个性化轮换策略面临工程门槛高、环境搭建难的挑战。为此，我们提出PersonaKit（PK），一个开源、低延迟的Web平台，支持通过直观的JSON配置快速构建对话角色，设定概率性打断处理行为（如让步、坚持、衔接或覆盖），并自动部署对比A/B测试。在野外环境下对8种不同人格的角色进行评估，证明PersonaKit提供了一个可扩展、端到端的研究框架，适用于下一代语音智能体中复杂社会语言行为的探索。
原文摘要 · Abstract (English)
As spoken dialogue systems expand beyond traditional assistant roles to encompass diverse personas -- such as authoritative instructors, uncooperative merchants, or distracted workers -- they require distinct, human-like turn-taking behaviors to maintain psychological immersion. However, current full-duplex systems often default to a rigid, overly accommodating ``always-yield'' policy during overlapping speech, which severely undermines character consistency for non-submissive roles. Evaluating alternative, persona-specific turn-taking strategies through empirical user studies is challenging because building real-time full-duplex test environments requires substantial engineering overhead. To address this, we present PersonaKit (PK), an open-source, low-latency web platform for the rapid prototyping and evaluation of conversational agents. Using intuitive JSON configurations, researchers can define personas, specify probabilistic interruption-handling behaviors (e.g., yield, hold, bridge, or override), and automatically deploy comparative A/B surveys. Through an in-the-wild evaluation with 8 distinct personas, we demonstrate that PersonaKit provides an extensible, end-to-end framework for studying complex sociolinguistic behaviors in next-generation spoken agents.
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。