话说太多、听得太少：社交机器人对话轮换问题分析
Robots That Talk Too Much and Don't Listen Enough
AI 导读
一篇提交至 HRI 2026 EMF Workshop 的 4 页短文回顾了早期改进社交机器人语音识别与对话轮换（turn-taking）的方法，指出语音识别的进步已大幅改善口语交互，但轮换失败和误解仍然频发。作者主张采用多模态双向流式处理来降低轮换失败率。
正文 · 原文
Abstract:Until recently, the biggest obstacles to natural spoken interaction with social robots were speech recognition errors and turn-taking failures. Advances in speech recognition have enabled much better spoken interaction, but turn-taking failures and other misunderstandings continue to be far too prevalent. This short paper looks back at earlier methods for improving speech recognition and turn-taking in interaction with social robots, and then looks at what can be done today, arguing that multimodal bidirectional streaming is needed to reduce the frequency of turn-taking failures.
| Comments: | 4 pages, 3 figures, presented at EMF Workshop, HRI 2026, Edinburgh, Scotland |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2611.16473 [cs.RO] |
| (or arXiv:2611.16473v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16473 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Graham Wilcock [view email]
[v1]
Thu, 12 Nov 2026 08:32:18 UTC (6,718 KB)
来源：arXiv cs.AI · arxiv.org