PulseAugur
中
实时 12:49:55
English(EN) Heard Enough to Act: Early Tool Calling in Spoken Dialogue Systems

新流程使语音代理在倾听时即可采取行动

研究人员开发了一种新颖的合成语音对话流程,以解决语音代理中的延迟挑战。该流程生成带有标注的对话,指示识别工具及其参数的最早时间点,使代理能够在倾听时即可采取行动,而不是等待整个回合完成。该系统构建了一个包含 26,694 个对话、跨越 48 个领域、总计 786 小时的语料库,并包含用于评估的 $\tau^2$-bench 的音频渲染。在该数据上训练的全模态语言模型在工具状态宏 F1 分数上达到了 0.48 和 0.47,与传统的回合结束级联方法相比,显示出显著的领先时间。 AI

影响 使语音代理能够通过处理部分转录内容来更快地响应,从而改善实时应用中的用户体验。

排序理由 学术论文,详细介绍了一种用于语音对话系统的新方法和数据集。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新流程使语音代理在倾听时即可采取行动

本文如何被排名

Signal score
8 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
学术论文,详细介绍了一种用于语音对话系统的新方法和数据集。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, infra
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
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Yizhou Peng, Chen Chen, Donghang Wu, Hexin Liu, Eng Siong Chng ·

    听够了就行动:语音对话系统中的早期工具调用

    arXiv:2610.34653v1 Announce Type: new Abstract: Latency-sensitive spoken agents must know not only which tool to call, but also when they have heard enough to act. Waiting for the turn to complete delays execution even when the request is already actionable. However, neither exis…