arXiv 2504.144822025-04-20cs.CLcs.SD

DialogueAgents：一种面向多方对话的混合智能体语音合成框架

DialogueAgents: A Hybrid Agent-Based Speech Synthesis Framework for Multi-Party Dialogue

State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications（网络与交换技术国家重点实验室，北京邮电大学）；Department of Computer Science and Engineering, Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）计算机科学与工程系）；Hong Kong University of Science and Technology（香港科技大学）

Xiang Li, Duyi Pan, Hongru Xiao, Jiale Han, Jing Tang, Jiabao Ma, Wei Wang, Bo Cheng

备注：: Accepted by ICME 2025. Dataset and code are publicly available: [https://github.com/uirlx/DialogueAgents](https://github.com/uirlx/DialogueAgents)

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出DialogueAgents混合智能体框架，通过脚本编写、语音合成与对话评论协作生成对话，并构建高质量双语多方对话数据集MultiTalk，实验验证其有效性。

摘要：

语音合成对于人机交互至关重要，能够实现自然直观的沟通。然而，现有数据集因人工标注而构建成本高昂，并且存在角色多样性、情境场景和情感表达性受限的问题。为解决这些问题，我们提出了DialogueAgents，一种新颖的基于混合智能体的语音合成框架，该框架集成了三个专业智能体——脚本编写者、语音合成器和对话评论家——以协同生成对话。基于多样化的角色池，该框架通过语音审查迭代优化对话脚本并合成语音，从而增强合成对话的情感表达性和副语言特征。利用DialogueAgents，我们贡献了MultiTalk，一个涵盖多样化主题的双语、多方、多轮语音对话数据集。大量实验证明了我们框架的有效性以及MultiTalk数据集的高质量。我们发布了数据集和代码https://github.com/uirlx/DialogueAgents，以促进未来在先进语音合成模型和定制数据生成方面的研究。

英文摘要：

Speech synthesis is crucial for human-computer interaction, enabling natural and intuitive communication. However, existing datasets involve high construction costs due to manual annotation and suffer from limited character diversity, contextual scenarios, and emotional expressiveness. To address these issues, we propose DialogueAgents, a novel hybrid agent-based speech synthesis framework, which integrates three specialized agents -- a script writer, a speech synthesizer, and a dialogue critic -- to collaboratively generate dialogues. Grounded in a diverse character pool, the framework iteratively refines dialogue scripts and synthesizes speech based on speech review, boosting emotional expressiveness and paralinguistic features of the synthesized dialogues. Using DialogueAgent, we contribute MultiTalk, a bilingual, multi-party, multi-turn speech dialogue dataset covering diverse topics. Extensive experiments demonstrate the effectiveness of our framework and the high quality of the MultiTalk dataset. We release the dataset and code https://github.com/uirlx/DialogueAgents to facilitate future research on advanced speech synthesis models and customized data generation.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。