Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2509.09716 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916959697764352 |
|---|---|
| author | Zhan, Jun Han, Mingyang Xie, Yuxuan Wang, Chen Zhang, Dong Huang, Kexin Shi, Haoxiang Wang, DongXiao Song, Tengtao Cheng, Qinyuan Li, Shimin Song, Jun Qiu, Xipeng Zheng, Bo |
| author_facet | Zhan, Jun Han, Mingyang Xie, Yuxuan Wang, Chen Zhang, Dong Huang, Kexin Shi, Haoxiang Wang, DongXiao Song, Tengtao Cheng, Qinyuan Li, Shimin Song, Jun Qiu, Xipeng Zheng, Bo |
| contents | Spoken language models (SLMs) have emerged as a unified paradigm for speech understanding and generation, enabling natural human machine interaction. However, while most progress has focused on semantic accuracy and instruction following, the ability of SLMs to adapt their speaking style based on spoken instructions has received limited attention. We introduce Voice Style Adaptation (VSA), a new task that examines whether SLMs can modify their speaking style, such as timbre, prosody, or persona following natural language spoken commands. To study this task, we present VStyle, a bilingual (Chinese & English) benchmark covering four categories of speech generation: acoustic attributes, natural language instruction, role play, and implicit empathy. We also introduce the Large Audio Language Model as a Judge (LALM as a Judge) framework, which progressively evaluates outputs along textual faithfulness, style adherence, and naturalness, ensuring reproducible and objective assessment. Experiments on commercial systems and open source SLMs demonstrate that current models face clear limitations in controllable style adaptation, highlighting both the novelty and challenge of this task. By releasing VStyle and its evaluation toolkit, we aim to provide the community with a foundation for advancing human centered spoken interaction. The dataset and code are publicly available at \href{https://junzhan2000.github.io/VStyle.github.io/}{project's homepage}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09716 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions Zhan, Jun Han, Mingyang Xie, Yuxuan Wang, Chen Zhang, Dong Huang, Kexin Shi, Haoxiang Wang, DongXiao Song, Tengtao Cheng, Qinyuan Li, Shimin Song, Jun Qiu, Xipeng Zheng, Bo Sound Artificial Intelligence Computation and Language Audio and Speech Processing Spoken language models (SLMs) have emerged as a unified paradigm for speech understanding and generation, enabling natural human machine interaction. However, while most progress has focused on semantic accuracy and instruction following, the ability of SLMs to adapt their speaking style based on spoken instructions has received limited attention. We introduce Voice Style Adaptation (VSA), a new task that examines whether SLMs can modify their speaking style, such as timbre, prosody, or persona following natural language spoken commands. To study this task, we present VStyle, a bilingual (Chinese & English) benchmark covering four categories of speech generation: acoustic attributes, natural language instruction, role play, and implicit empathy. We also introduce the Large Audio Language Model as a Judge (LALM as a Judge) framework, which progressively evaluates outputs along textual faithfulness, style adherence, and naturalness, ensuring reproducible and objective assessment. Experiments on commercial systems and open source SLMs demonstrate that current models face clear limitations in controllable style adaptation, highlighting both the novelty and challenge of this task. By releasing VStyle and its evaluation toolkit, we aim to provide the community with a foundation for advancing human centered spoken interaction. The dataset and code are publicly available at \href{https://junzhan2000.github.io/VStyle.github.io/}{project's homepage}. |
| title | VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions |
| topic | Sound Artificial Intelligence Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2509.09716 |