Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.25434 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917376722731008 |
|---|---|
| author | Shen, Huan Wang, Yingao Huang, Shangkun Zou, Wei Chen, Yunzhang |
| author_facet | Shen, Huan Wang, Yingao Huang, Shangkun Zou, Wei Chen, Yunzhang |
| contents | Turn-taking modeling is fundamental to spoken dialogue systems, yet its evaluation remains fragmented and often limited to binary boundary detection under narrow interaction settings. Such protocols hinder systematic comparison and obscure model weaknesses across conversational conditions. We present CoDeTT, a context-aware decision benchmark for turn-taking evaluation. CoDeTT formulates turn-taking as a structured decision problem and constructs a multi-scenario dataset with fine-grained decision categories and controlled context variations. Under a unified evaluation protocol, we assess representative existing models and observe substantial performance disparities across decision types and interaction scenarios. CoDeTT provides a standardized benchmark for systematic and context-aware evaluation of turn-taking systems. The benchmark dataset and evaluation toolkit are available at https://yingaowang-casia.github.io/CoDeTT.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_25434 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CoDeTT: A Context-Aware Decision Benchmark for Turn-Taking Evaluation Shen, Huan Wang, Yingao Huang, Shangkun Zou, Wei Chen, Yunzhang Sound Turn-taking modeling is fundamental to spoken dialogue systems, yet its evaluation remains fragmented and often limited to binary boundary detection under narrow interaction settings. Such protocols hinder systematic comparison and obscure model weaknesses across conversational conditions. We present CoDeTT, a context-aware decision benchmark for turn-taking evaluation. CoDeTT formulates turn-taking as a structured decision problem and constructs a multi-scenario dataset with fine-grained decision categories and controlled context variations. Under a unified evaluation protocol, we assess representative existing models and observe substantial performance disparities across decision types and interaction scenarios. CoDeTT provides a standardized benchmark for systematic and context-aware evaluation of turn-taking systems. The benchmark dataset and evaluation toolkit are available at https://yingaowang-casia.github.io/CoDeTT.github.io/. |
| title | CoDeTT: A Context-Aware Decision Benchmark for Turn-Taking Evaluation |
| topic | Sound |
| url | https://arxiv.org/abs/2603.25434 |