AffAdapt：面向流畅对话的情感驱动型自适应AI角色
AffAdapt: AFFect-driven ADAPTive AI Personas for Seamless Conversations
浏览论文内容
中文总结 AI 辅助
研究提出AffAdapt框架，整合多模块构建AI角色交互循环，实现流畅人机对话，在高风险对话场景验证其有效性，指出相关挑战并说明其应用场景。
中文摘要 AI 辅助
AI生成的角色正越来越多地用于支持、培训和模拟场景。虽然生成式AI模型具备生成感知情感的响应的能力，但将其具象化为视觉角色仍是当前研究的活跃领域。自然的对话需要理解对话伙伴的话轮完成情况，智能体应响应还是继续倾听，并依赖与自身情绪状态一致的非语言线索。在多模态环境中实现流畅的人机对话，要求所有生成的模态协同工作。我们提出AffAdapt，一个用于AI角色的流畅交互设计框架，它将流式语音识别、主动话轮管理、基于角色的响应生成、持久的情绪状态以及同步的具象化输出整合为单一交互循环。我们在练习敏感、高风险对话的场景中展示了该架构，并报告了一项初步案例研究，显示其具备流畅的话轮管理和自适应、符合角色的行为，同时指出了在中断处理、开放式对话和多模态情感对齐方面的开放性挑战。AffAdapt的交互循环是一种可推广的模式，用于协调实时AI角色的时机、身份和情感，适用于培训、指导、教育和模拟等任何需要可信、响应式交互的场景。
英文摘要
AI-generated personas are being increasingly used for support, training and simulations. While generative AI models possess abilities to generate affect-aware responses, their embodiment into visual personas is an active area of investigation. Naturalistic exchanges require understanding of the conversational partners' turn completions, whether the agent should respond or keep listening and rely on non-verbal cues aligned with one's emotional states. Seamless human-AI conversation in a multimodal setting requires all modalities being generated to act in coordination. We present AffAdapt, a seamless interaction design framework for AI-personas, which coordinates streaming speech recognition, proactive turn-management, persona-grounded response generation, a persistent emotional state, and synchronized embodied output into a single interaction loop. We demonstrate the architecture in the context of practicing sensitive, high-stakes conversations, and report an initial case study showing fluid turn management and adaptive, persona-consistent behavior, alongside open challenges in interruption handling, open-ended dialogue, and multimodal affective alignment. AffAdapt's interaction loop is a generalizable pattern for coordinating timing, identity, and affect in real-time AI personas - applicable to training, coaching, education, and simulation contexts wherever believable, responsive interaction matters.
