让语音对话模型按指定时长生成回应，提升人机交互自然度。
TiCo: Time-Controllable Spoken Dialogue Model
- 用语音时间标记动态感知生成时长，实现精准控时。
- 响应时长误差降低2.7倍，且保持高质量输出。
- 适合语音助手、智能客服等需精准时长控制的场景。
我们提出TiCo，一种可按时间约束生成语音对话的模型（如“请生成约15秒的回应”），能控制语音响应时长。该能力对语音助手和交互式代理等真实场景至关重要。现有模型虽能生成自然语音，但缺乏时间意识，难以满足时长指令。为此，我们构建了首个评估时间可控指令遵循的基准测试集TiCo-Bench，发现主流开源与商用模型常无法满足显式时长要求。TiCo通过在生成中引入语音时间标记（STM，如<10.6秒>），使模型实时感知已用时长，并调整剩余内容以达成目标时长。该方法无需问答配对数据，仅通过自生成与可验证奖励的强化学习高效后训练。实验表明，相较于基线模型，TiCo将时长误差降低2.7倍，优于最强基线1.6倍，同时维持高响应质量。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。