English(EN) Low-Latency Turn-Taking via Context-Aware Preface Generation in a Real-World Dialogue Robot

AI对话系统应对轮次转换和延迟挑战

作者 PulseAugur 编辑部 · [2 个来源] · 2026-07-28 04:00

两篇新的研究论文探讨了提高人机对话的自然性和效率的方法。第一篇，DuplexGen，通过根据人类偏好校准LLM预测，专注于生成具有场景自适应轮次转换的对话。第二篇论文介绍了一个用于对话机器人的两阶段增量框架，该框架将前缀响应准备与语音开始分离，以减少延迟，并在真实的购物中心实验中进行了测试。 AI

影响这些进展旨在使AI交互更加流畅和响应迅速，有可能改善用户在对话代理和机器人中的体验。

排序理由两篇在arXiv上发表的学术论文，详细介绍了AI对话系统的新方法。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 两篇在arXiv上发表的学术论文，详细介绍了AI对话系统的新方法。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 72 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Takyoung Kim, Kang-wook Kim, Sang Hoon Woo, Julia Hirschberg, Gunhee Kim, Dilek Hakkani-T\"ur · 2026-07-30 04:00

DuplexGen：人类-AI轮流对话的自适应合成

arXiv:2607.26178v1 Announce Type: new Abstract: Turn-taking is a central component of full-duplex interaction. Which turn-taking behaviors are appropriate varies with the scenario, yet current models apply a single norm regardless of context. This limitation originates in their t…
arXiv cs.CL TIER_1 English(EN) · Yuki Okafuji, Koji Inoue, Yoshiki Ohira · 2026-07-28 04:00

通过上下文感知前缀生成实现低延迟轮次转换：在真实对话机器人中的应用

arXiv:2607.23204v1 Announce Type: cross Abstract: Large language model (LLM)-based dialogue systems suffer response delays because generation begins only after final speech recognition. While fixed fillers are a workaround, they become unnatural over time. We propose a two-stage …