AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910111035817984 |
|---|---|
| author | Li, Wenyu Jiao, Xiaoqi Chang, Yi Zhang, Guangyan Guo, Yiwen |
| author_facet | Li, Wenyu Jiao, Xiaoqi Chang, Yi Zhang, Guangyan Guo, Yiwen |
| contents | The creation of high-quality multimodal datasets remains fundamental for advancing role-playing capabilities in large language models (LLMs). While existing works predominantly focus on text-based persona simulation, Audio Role-Playing (ARP) presents unique challenges due to the need for synchronized alignment of semantic content and vocal characteristics. To address this gap, we propose AudioRole, a meticulously curated dataset from 13 TV series spanning 1K+ hours with 1M+ character-grounded dialogues, providing synchronized audio-text pairs annotated with speaker identities and contextual metadata. In addition, to demonstrate the effectiveness of the dataset, we introduced ARP-Eval, a dual-aspect evaluation framework that assesses both response quality and role fidelity. Empirical validation showing GLM-4-Voice trained on AudioRole (which we called ARP-Model) achieve an average Acoustic Personalization score of 0.31, significantly outperforming the original GLM-4-voice and the more powerful model MiniCPM-O-2.6, which specifically supports role-playing in one-shot scenarios. The ARP-Model also achieves a Content Personalization score of 0.36, surpassing the untrained original model by about 38% and maintaining the same level as MiniCPM-O-2.6.
AudioRole features dialogues from over 115 main characters, 6 trained ARP-Models that role-play different characters, and evaluation protocols. Together, they provide an essential resource for advancing audio-grounded role-playing research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23435 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models Li, Wenyu Jiao, Xiaoqi Chang, Yi Zhang, Guangyan Guo, Yiwen Sound Artificial Intelligence Multimedia Audio and Speech Processing The creation of high-quality multimodal datasets remains fundamental for advancing role-playing capabilities in large language models (LLMs). While existing works predominantly focus on text-based persona simulation, Audio Role-Playing (ARP) presents unique challenges due to the need for synchronized alignment of semantic content and vocal characteristics. To address this gap, we propose AudioRole, a meticulously curated dataset from 13 TV series spanning 1K+ hours with 1M+ character-grounded dialogues, providing synchronized audio-text pairs annotated with speaker identities and contextual metadata. In addition, to demonstrate the effectiveness of the dataset, we introduced ARP-Eval, a dual-aspect evaluation framework that assesses both response quality and role fidelity. Empirical validation showing GLM-4-Voice trained on AudioRole (which we called ARP-Model) achieve an average Acoustic Personalization score of 0.31, significantly outperforming the original GLM-4-voice and the more powerful model MiniCPM-O-2.6, which specifically supports role-playing in one-shot scenarios. The ARP-Model also achieves a Content Personalization score of 0.36, surpassing the untrained original model by about 38% and maintaining the same level as MiniCPM-O-2.6. AudioRole features dialogues from over 115 main characters, 6 trained ARP-Models that role-play different characters, and evaluation protocols. Together, they provide an essential resource for advancing audio-grounded role-playing research. |
| title | AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models |
| topic | Sound Artificial Intelligence Multimedia Audio and Speech Processing |
| url | https://arxiv.org/abs/2509.23435 |