The ICASSP 2026 HumDial Challenge: Benchmarking Human-like Spoken Dialogue Systems in the LLM Era
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917246696161280 |
|---|---|
| author | Zhao, Zhixian Wang, Shuiyuan Li, Guojian Xue, Hongfei Wang, Chengyou Wang, Shuai Xiao, Longshuai Zhang, Zihan Bu, Hui Xu, Xin Wang, Xinsheng Liu, Hexin Chng, Eng Siong Lee, Hung-yi Xie, Lei |
| author_facet | Zhao, Zhixian Wang, Shuiyuan Li, Guojian Xue, Hongfei Wang, Chengyou Wang, Shuai Xiao, Longshuai Zhang, Zihan Bu, Hui Xu, Xin Wang, Xinsheng Liu, Hexin Chng, Eng Siong Lee, Hung-yi Xie, Lei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05564 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The ICASSP 2026 HumDial Challenge: Benchmarking Human-like Spoken Dialogue Systems in the LLM Era Zhao, Zhixian Wang, Shuiyuan Li, Guojian Xue, Hongfei Wang, Chengyou Wang, Shuai Xiao, Longshuai Zhang, Zihan Bu, Hui Xu, Xin Wang, Xinsheng Liu, Hexin Chng, Eng Siong Lee, Hung-yi Xie, Lei Sound Computation and Language Human-Computer Interaction Audio and Speech Processing 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. |
| title | The ICASSP 2026 HumDial Challenge: Benchmarking Human-like Spoken Dialogue Systems in the LLM Era |
| topic | Sound Computation and Language Human-Computer Interaction Audio and Speech Processing |
| url | https://arxiv.org/abs/2601.05564 |