arXiv 2509.204102026-09-04eess.AScs.SD

Phoenix-VAD：用于全双工语音交互的流式语义端点检测

Phoenix-VAD: Streaming Semantic Endpoint Detection for Full-Duplex Speech Interaction

School of Informatics, Xiamen University, China（厦门大学信息学院）；School of Electronic Science and Engineering, Xiamen University, China（厦门大学电子科学与技术学院）；DiDi Global Inc., Beijing, China（滴滴全球有限公司）

Weijie Wu, Wenhao Guan, Kaidi Wang, Peijie Chen, Zhuanling Zha, Junbo Li, Jun Fang, Lin Li, Qingyang Hong

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有口语对话模型缺少即插即用全双工语义端点检测模块的问题，提出基于LLM的Phoenix-VAD模型，通过滑动窗口训练实现流式推理，在两类语音场景下表现优异，且模块可独立优化，助力下一代人机交互。

摘要：

口语对话模型已显著推动智能人机交互发展，但缺乏即插即用的全双工语义端点检测预测模块，阻碍了无缝音频交互。本文提出Phoenix-VAD，一种基于大语言模型（LLM）的模型，可实现流式语义端点检测。具体而言，Phoenix-VAD利用LLM的语义理解能力和滑动窗口训练策略，在支持流式推理的同时实现可靠的语义端点检测。对语义完整及不完整语音场景的实验表明，Phoenix-VAD取得了优异且有竞争力的性能。此外，该设计使全双工预测模块可独立于对话模型优化，为下一代人机交互提供更可靠、灵活的支持。

英文摘要：

Spoken dialogue models have significantly advanced intelligent human-computer interaction, yet they lack a plug-and-play full-duplex prediction module for semantic endpoint detection, hindering seamless audio interactions. In this paper, we introduce Phoenix-VAD, an LLM-based model that enables streaming semantic endpoint detection. Specifically, Phoenix-VAD leverages the semantic comprehension capability of the LLM and a sliding window training strategy to achieve reliable semantic endpoint detection while supporting streaming inference. Experiments on both semantically complete and incomplete speech scenarios indicate that Phoenix-VAD achieves excellent and competitive performance. Furthermore, this design enables the full-duplex prediction module to be optimized independently of the dialogue model, providing more reliable and flexible support for next-generation human-computer interaction.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。