StyleBench: Evaluating Speech Language Models on Conversational Speaking Style Control
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912952071749632 |
|---|---|
| author | Zhao, Haishu Hao, Aokai Ge, Yuan Hong, Zhenqiang Xiao, Tong Zhu, Jingbo |
| author_facet | Zhao, Haishu Hao, Aokai Ge, Yuan Hong, Zhenqiang Xiao, Tong Zhu, Jingbo |
| contents | Speech language models (SLMs) have significantly extended the interactive capability of text-based Large Language Models (LLMs) by incorporating paralinguistic information. For more realistic interactive experience with customized styles, current SLMs have managed to interpret and control speaking style intensity from user prompts during the dialogue process. However, there remains a lack of systematic benchmarks that quantifies and evaluates the style intensity control ability in conversations. In this paper, we propose StyleBench, a multi-turn dialogue benchmark for comprehensively evaluating the style intensity control ability across four dimensions: emotion, speed, volume, and pitch. Our results reveal the performance gaps between leading SLMs and omni language models (OLMs), suggesting the underlying reasons and promising approaches for future exploration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07599 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | StyleBench: Evaluating Speech Language Models on Conversational Speaking Style Control Zhao, Haishu Hao, Aokai Ge, Yuan Hong, Zhenqiang Xiao, Tong Zhu, Jingbo Computation and Language Speech language models (SLMs) have significantly extended the interactive capability of text-based Large Language Models (LLMs) by incorporating paralinguistic information. For more realistic interactive experience with customized styles, current SLMs have managed to interpret and control speaking style intensity from user prompts during the dialogue process. However, there remains a lack of systematic benchmarks that quantifies and evaluates the style intensity control ability in conversations. In this paper, we propose StyleBench, a multi-turn dialogue benchmark for comprehensively evaluating the style intensity control ability across four dimensions: emotion, speed, volume, and pitch. Our results reveal the performance gaps between leading SLMs and omni language models (OLMs), suggesting the underlying reasons and promising approaches for future exploration. |
| title | StyleBench: Evaluating Speech Language Models on Conversational Speaking Style Control |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2603.07599 |