Enabling Conversational Behavior Reasoning Capabilities in Full-Duplex Speech
This work addresses the challenge of building natural conversational AI systems for applications like speech interfaces, though it appears incremental as it builds on existing causal and graph-based methods.
The paper tackles the problem of modeling implicit thought chains in human conversation to improve full-duplex interactive systems, introducing a Graph-of-Thoughts framework that predicts speech acts and intents with causal inference, achieving robust behavior detection and interpretable reasoning in experiments on synthetic and real dialogues.
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.