TiCo：时间可控的语音对话模型
TiCo: Time-Controllable Spoken Dialogue Model
AI总结：
TiCo是一种能遵循时间约束指令生成可控时长语音响应的对话模型，通过引入时间标记器提升对时间的感知能力，有效减少响应时长误差。
摘要：
我们介绍了TiCo，一种时间可控的语音对话模型（SDM），能够遵循时间约束指令（例如"请生成约15秒的响应"）并生成具有可控时长的语音响应。这种能力对于实际语音系统如语音助手和交互代理非常重要，因为控制响应时长可以提高交互质量。然而，尽管现有模型能生成自然的语音响应，但缺乏时间意识，难以遵循与时长相关的指令。为此，我们引入了TiCo-Bench，这是首个用于评估SDM中时间可控指令遵循的基准，现有开源和商业模型在该基准上常无法满足显式时间约束。TiCo通过在生成过程中利用语音时间标记器（STM）（例如<10.6秒）来估计已过说话时间，从而使SDM能够保持对时间的意识并调整剩余内容以满足目标时长。TiCo通过自生成和强化学习高效地进行微调，无需问答配对数据。实验结果表明，TiCo在保持响应质量的同时，其基线模型的时长误差减少了2.7倍，最强基线模型的误差减少了1.6倍。
英文摘要：
We introduce TiCo, a time-controllable spoken dialogue model (SDM) that follows time-constrained instructions (e.g., "Please generate a response lasting about 15 seconds") and generates spoken responses with controllable duration. This capability is valuable for real-world spoken language systems such as voice assistants and interactive agents, where controlling response duration can improve interaction quality. However, despite their strong ability to generate natural spoken responses, existing models lack time awareness and struggle to follow duration-related instructions. To systematically evaluate this, we introduce TiCo-Bench, the first benchmark for time-controllable instruction following in SDMs, on which existing open-source and commercial models frequently fail to satisfy explicit time constraints. TiCo addresses this limitation by enabling an SDM to estimate elapsed speaking time during generation through Spoken Time Markers (STM) (e.g., <10.6 seconds>). These markers help the model maintain awareness of time and adjust the remaining content to meet the target duration. TiCo is post-trained efficiently without question-answer paired data, relying on self-generation and reinforcement learning with verifiable reward. Experimental results show that TiCo reduces duration error by 2.7x over its backbone and 1.6x over the strongest baseline, while preserving response quality.
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。
