沉默的思维：通过潜在推理建模全双工语音对话模型中的内部认知
The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning
AI总结：
本文提出了一种名为FLAIR的全双工语音对话模型，通过潜在推理同时进行语音感知和内部思考，以提高对话质量，该方法在多个语音基准测试中取得了竞争性的结果。
摘要：
在对话互动中，人类在听讲者说话时会潜意识地进行同时思考。尽管这种内部认知处理可能不总是表现为显式的语言结构，但它是制定高质量响应的关键。受这一认知现象的启发，我们提出了一种名为FLAIR的新全双工潜在和内部推理方法，该方法在语音感知的同时进行潜在思考。与传统NLP中的“思考”机制不同，我们的方法不需要事后生成，而是无缝地与语音对话系统结合：在用户说话阶段，它将前一步的潜在嵌入输出递归地馈入下一步，从而实现连续推理，严格遵循因果性而不引入额外延迟。为了实现这种潜在推理，我们设计了一个基于证据下界的目标，支持通过教师强制进行高效的监督微调，从而避免了需要显式推理注释的需要。实验表明，这种听的同时思考设计在多个语音基准测试中均取得了竞争性的结果。此外，FLAIR能够稳健地处理对话动态，并在全双工交互指标上取得了竞争性的性能。
英文摘要：
During conversational interactions, humans subconsciously engage in concurrent thinking while listening to a speaker. Although this internal cognitive processing may not always manifest as explicit linguistic structures, it is instrumental in formulating high-quality responses. Inspired by this cognitive phenomenon, we propose a novel Full-duplex LAtent and Internal Reasoning method named FLAIR that conducts latent thinking simultaneously with speech perception. Unlike conventional "thinking" mechanisms in NLP, which require post-hoc generation, our approach aligns seamlessly with spoken dialogue systems: during the user's speaking phase, it recursively feeds the latent embedding output from the previous step into the next step, enabling continuous reasoning that strictly adheres to causality without introducing additional latency. To enable this latent reasoning, we design an Evidence Lower Bound-based objective that supports efficient supervised finetuning via teacher forcing, circumventing the need for explicit reasoning annotations. Experiments demonstrate the effectiveness of this think-while-listening design, which achieves competitive results on a range of speech benchmarks. Furthermore, FLAIR robustly handles conversational dynamics and attains competitive performance on full-duplex interaction metrics.
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。
