arXiv cs.CL· Hien Ohnaka, Kazuyo Onishi, Koichiro Yoshino·· 11 小时前AI 评分18
面向语音对话系统的实时短响应选择任务
Real-Time Short-Response Selection for Spoken Dialogue Systems
AI 导读
研究提出实时短响应选择任务，可与现有轮次转换模型集成，用于掩盖语言生成与语音合成造成的延迟。模型用对比学习学习对话上下文与短响应的映射，在检测到轮次转换事件时从预生成候选中选出一条先播放。实验显示该方法能基于对话上下文选择短响应，优于随机和基于 LLM 的基线，且集成后轮次转换预测性能保持不变、处理开销极小。
正文 · 原文
Abstract:To realize spoken dialogue systems that can interact naturally with users, it is important for the system to respond to user utterances at appropriate timings. To achieve such natural turn-taking, the system needs not only to predict appropriate response timings but also to mask delays caused by language generation and speech synthesis so that they are not perceived by the user. We propose a real-time short-response selection task that can be integrated with existing turn-taking models to mask generation delay. To address this task, the proposed model learns the mapping between dialogue context and short responses using contrastive learning. When a turn-taking event is detected, the system selects a response from a set of pre-generated candidates. The selected response is played while the main response is being generated. Experimental results show that the proposed method learns to select short responses based on dialogue context, outperforming random and LLM-based baselines. Moreover, integrating response selection maintained turn-taking prediction performance and added minimal processing overhead.
| Comments: | 10 pages, 2 figures, 7 tables |
| Subjects: | Sound (cs.SD); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.09057 [cs.SD] |
| (or arXiv:2611.09057v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2611.09057 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hien Ohnaka [view email]
[v1]
Fri, 6 Nov 2026 06:32:54 UTC (376 KB)
来源：arXiv cs.CL · arxiv.org