实现全双工语音中对话行为推理能力
Enabling Conversational Behavior Reasoning Capabilities in Full-Duplex Speech
AI总结：
本文提出一种基于图的思维框架，通过建模对话行为的因果推断，实现全双工语音交互中的行为推理与可解释性。
摘要：
人类对话是由隐含的思想链组织起来的，表现为时间有序的言语行为。捕捉这种因果路径是构建自然全双工交互系统的关键。我们介绍了一个框架，通过将此过程建模为图中的因果推断（Graph-of-Thoughts, GoT）来实现对话行为的推理。我们的方法通过分层标签方案正式化意图-行为路径，预测高层通信意图和低层言语行为，以学习其因果和时间依赖性。为训练此系统，我们开发了一个混合语料库，将可控、事件丰富的模拟与人工标注的推理和真实对话语音相结合。GoT框架将流式预测结构化为一个演进图，使多模态Transformer能够预测下一个言语行为，生成简洁的决策依据，并动态完善其推理。在合成和真实双工对话上的实验表明，该框架能够实现稳健的行为检测，产生可解释的推理链，并为全双工语音对话系统中的对话推理建立基准基础。
英文摘要：
Human conversation is organized by an implicit chain of thoughts that manifests as timed speech acts. Capturing this causal pathway is key to building natural full-duplex interactive systems. We introduce a framework that enables reasoning over conversational behaviors by modeling this process as causal inference within a Graph-of-Thoughts (GoT). Our approach formalizes the intent-to-action pathway with a hierarchical labeling scheme, predicting high-level communicative intents and low-level speech acts to learn their causal and temporal dependencies. To train this system, we develop a hybrid corpus that pairs controllable, event-rich simulations with human-annotated rationales and real conversational speech. The GoT framework structures streaming predictions as an evolving graph, enabling a multimodal transformer to forecast the next speech act, generate concise justifications for its decisions, and dynamically refine its reasoning. Experiments on both synthetic and real duplex dialogues show that the framework delivers robust behavior detection, produces interpretable reasoning chains, and establishes a foundation for benchmarking conversational reasoning in full duplex spoken dialogue systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
