思考、言语化、再说话：桥接复杂思维与可理解语音
Think, Verbalize, then Speak: Bridging Complex Thoughts and Comprehensible Speech
AI总结：
本文提出Think-Verbalize-Speak框架，通过引入言语化中间步骤和低延迟言语化器ReVerT，将LLM推理与语音表达解耦，在保持推理能力的同时提升语音自然度和简洁性。
摘要：
口语对话系统越来越多地采用大语言模型（LLMs）以利用其先进的推理能力。然而，在口语交流中直接应用LLMs往往产生次优结果，因为最优文本表达与口头表达之间存在不匹配。尽管现有方法调整LLMs以生成适合语音的输出，但它们对推理性能的影响仍未得到充分探索。本文提出Think-Verbalize-Speak框架，将推理与语音表达解耦，以保留LLMs的完整推理能力。该方法的核心是言语化（verbalizing），一个将思维转化为自然、适合语音的文本的中间步骤。我们还引入ReVerT，一个基于增量式异步摘要的低延迟言语化器。在多个基准上的实验表明，该方法在提升语音自然度和简洁性的同时，对推理的影响最小。项目页面（含数据集和源代码）见 https://yhytoto12.github.io/TVS-ReVerT。
英文摘要：
Spoken dialogue systems increasingly employ large language models (LLMs) to leverage their advanced reasoning capabilities. However, direct application of LLMs in spoken communication often yield suboptimal results due to mismatches between optimal textual and verbal delivery. While existing approaches adapt LLMs to produce speech-friendly outputs, their impact on reasoning performance remains underexplored. In this work, we propose Think-Verbalize-Speak, a framework that decouples reasoning from spoken delivery to preserve the full reasoning capacity of LLMs. Central to our method is verbalizing, an intermediate step that translates thoughts into natural, speech-ready text. We also introduce ReVerT, a latency-efficient verbalizer based on incremental and asynchronous summarization. Experiments across multiple benchmarks show that our method enhances speech naturalness and conciseness with minimal impact on reasoning. The project page with the dataset and the source code is available at https://yhytoto12.github.io/TVS-ReVerT
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。
