arXiv 2509.222432025-09-26cs.CL

FLEXI：全双工人类-LLM语音交互基准测试

FLEXI: Benchmarking Full-duplex Human-LLM Speech Interaction

School of Computer Science and Engineering, Northeastern University, Shenyang, China（计算机科学与工程学院，东北大学，沈阳，中国）；NiuTrans Research（NiuTrans研究）；Kunming University of Science and Technology（昆明理工大学）

Yuan Ge, Saihan Chen, Jingqi Xiao, Xiaoqian Liu, Tong Xiao, Yan Xiang, Zhengtao Yu, Jingbo Zhu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出FLEXI基准，通过六类场景评估全双工语音LLM的延迟、质量与交互有效性，发现开源与商业模型在紧急意识等方面存在显著差距。

摘要：

全双工语音到语音大型语言模型（LLM）是自然人机交互的基础，可实现实时口语对话系统。然而，对这些模型进行基准测试和建模仍是一项根本性挑战。我们提出FLEXI，这是首个面向全双工LLM-人类口语交互的基准，明确纳入紧急场景中的模型打断能力。FLEXI通过六个多样化的人类-LLM交互场景，系统评估实时对话的延迟、质量和会话有效性，揭示了开源模型与商业模型在紧急意识、话轮终止和交互延迟方面的显著差距。最后，我们认为下一个token对预测为实现真正无缝且类人的全双工交互提供了一条有前景的路径。

英文摘要：

Full-Duplex Speech-to-Speech Large Language Models (LLMs) are foundational to natural human-computer interaction, enabling real-time spoken dialogue systems. However, benchmarking and modeling these models remains a fundamental challenge. We introduce FLEXI, the first benchmark for full-duplex LLM-human spoken interaction that explicitly incorporates model interruption in emergency scenarios. FLEXI systematically evaluates the latency, quality, and conversational effectiveness of real-time dialogue through six diverse human-LLM interaction scenarios, revealing significant gaps between open source and commercial models in emergency awareness, turn terminating, and interaction latency. Finally, we suggest that next token-pair prediction offers a promising path toward achieving truly seamless and human-like full-duplex 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。