Papers

何时该开口说话?针对土耳其语的语音对话轮次结束检测研究

When Should a Voice Agent Speak? End-of-Turn Detection in Turkish

Why we picked it

做语音智能体的朋友应该看看这篇:它用土耳其语通话数据实测了"用户说完没有"怎么判断。结论很实在,微调 TurnGPT 加说话人计时特征效果最好,比固定静音等待既少打断又更快响应,还有延迟仿真数据支撑。

该研究针对语音智能体在对话中如何判断"用户说完了还是只是停顿"这一核心问题,基于 Real-TurnTurk 土耳其语双人视频通话语料库,提取轮次结束与轮次内停顿两类样本进行建模。实验比较了微调的土耳其语 TurnGPT 模型、零样本土耳其语语言模型和一个已部署的多语言检测器,并加入语音活动计时特征与面部特征,采用录音不相交与说话人不相交两种评估方式,配合配对聚类 bootstrap 检验。在留出录音上,微调 TurnGPT 区分轮次结束与停顿的能力优于两个文本基线,且是三者中校准最好的。计时特征同样具有较高信息量,将其与微调文本分数结合(logistic regression)取得基于时间信息的最佳结果,也优于与两个文本基线组合的版本。延迟仿真显示,在固定静音超时基础上加入文本分数,可在相同打断率下缩短平均响应延迟;在 Whisper 自动转录文本上,微调模型仍保持对零样本模型的优势。

Body

对开发者而言,这项工作说明固定静音时长这一常见做法存在明显瓶颈:说话人自身的计时特征与文本分数结合是更优的判据组合。对企业部署多语言语音智能体的团队来说,研究还提示零样本语言模型在轮次检测上不如微调模型可靠,且这一结论在自动转录(Whisper)条件下依然成立。

Original · arXiv cs.AI

When Should a Voice Agent Speak? End-of-Turn Detection in Turkish

A voice agent that waits for a fixed silence before replying either interrupts users who pause mid-utterance or responds late to users who have finished. This study examines the decision at the onset of silence, using turn ends and turn-internal pauses extracted from the Real-TurnTurk corpus of Turkish dyadic video calls. A fine-tuned Turkish TurnGPT model, a zero-shot Turkish language model and a deployed multilingual detector are compared, together with voice-activity timing and facial features, under recording-disjoint and speaker-disjoint evaluation with paired cluster bootstrap tests. On held-out recordings, the fine-tuned model separates turn ends from pauses better than both text baselines and is the best calibrated of the three. Timing features of the current speaker are similarly informative, and their combination with the fine-tuned text score gives the best timing-based results; with logistic regression, this combination also outperforms the same combination with either text baseline. In a latency simulation, adding the text score to a silence timeout shortens the mean response delay at the same interruption rate. On automatic Whisper transcripts, the fine-tuned model retains its advantage over the zero-shot model.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include TurnGPT, Whisper, voice agents.

Source attribution: curated from arXiv cs.AI (@Ahmet Tuğrul Bayrak, Fatma Nur Korkmaz, Mustafa Sertaç Türkel, Nur Yağmur Tuncer).