ICASSP 2026 挑战赛评测大模型时代的类人对话系统能力
The ICASSP 2026 HumDial Challenge: Benchmarking Human-like Spoken Dialogue Systems in the LLM Era
- 分情感智能与全双工交互双赛道评估对话系统
- 基于真实人类对话数据集，测试长期情绪理解与实时响应
- 适合关注对话系统智能化、人机交互的研究者
随着大语言模型（LLMs），特别是音频大模型和全能模型的快速发展，语音对话系统已显著进步，逐步缩小人机与人际交流之间的差距。实现真正‘类人’沟通需要双重能力：感知并共鸣用户情绪的情感智能，以及应对对话动态自然流的稳健交互机制，如实时轮换发言。因此，我们在 ICASSP 2026 发起首届类人语音对话系统挑战赛（HumDial），用于评测这两项核心能力。该挑战基于大规模真实人类对话数据集，设立两个赛道：（1）情感智能，聚焦长期情绪理解与共情生成；（2）全双工交互，系统性评估在‘边听边说’条件下的实时决策能力。本文总结了数据集构建、赛道设置及最终结果。
原文摘要 · Abstract (English)
Driven by the rapid advancement of Large Language Models (LLMs), particularly Audio-LLMs and Omni-models, spoken dialogue systems have evolved significantly, progressively narrowing the gap between human-machine and human-human interactions. Achieving truly ``human-like'' communication necessitates a dual capability: emotional intelligence to perceive and resonate with users' emotional states, and robust interaction mechanisms to navigate the dynamic, natural flow of conversation, such as real-time turn-taking. Therefore, we launched the first Human-like Spoken Dialogue Systems Challenge (HumDial) at ICASSP 2026 to benchmark these dual capabilities. Anchored by a sizable dataset derived from authentic human conversations, this initiative establishes a fair evaluation platform across two tracks: (1) Emotional Intelligence, targeting long-term emotion understanding and empathetic generation; and (2) Full-Duplex Interaction, systematically evaluating real-time decision-making under `` listening-while-speaking'' conditions. This paper summarizes the dataset, track configurations, and the final results.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。