arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.09413eess.AS
收藏

在丰富语境中评估语音的表达恰当性

Evaluating the Expressive Appropriateness of Speech in Rich Contexts

Shanghai Jiao Tong University(上海交通大学);Kuaishou Technology(快手科技);TeleAI(中国电信人工智能研究院);National University of Singapore(新加坡国立大学);Tencent(腾讯)
Tianrui Wang, Ziyang Ma, Yizhou Peng, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao, Yu Jiang, Yuheng Lu, Guanrou Yang, Xuanchen Li, Hexin Liu, C… 展开作者

Tianrui Wang, Ziyang Ma, Yizhou Peng, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao, Yu Jiang, Yuheng Lu, Guanrou Yang, Xuanchen Li, Hexin Liu, Chunyu Qiang, Cheng Gong, Yifan Yang, Tianchi Liu, Junyu Wang, Nana Hou, Meng Ge, Fuming You, Wei Yang, Zhongqian Sun, Haifeng Hu, Xiaobao Wang, Eng Siong Chng, Xie Chen, Longbiao Wang, Jianwu Dang

AI总结:

本文提出CEAEval框架,通过结合叙事上下文评估语音表达是否恰当,构建了首个中文对话语音语料库,并开发了CEAEval-M模型,显著提升了语音评估性能。

摘要:

评估表达性语音仍然具有挑战性,因为现有方法主要评估情感强度,而忽略了语音样本是否适合其语境设置。这种限制阻碍了用于叙事驱动和交互应用的语音系统的可靠评估,如有声书和对话代理。我们引入CEAEval,一个用于评估语音表达恰当性的丰富语境框架,该框架评估语音样本是否在语篇层面的叙事语境中表达恰当。为支持此任务,我们构建了CEAEval-D,首个包含真实人类表演的中文对话语音语料库,提供叙事描述及十五个维度的人类注释,涵盖表达属性和表达恰当性。我们进一步开发了CEAEval-M,整合知识蒸馏、基于规划的多模型协作、自适应音频注意力偏差和强化学习,以执行丰富表达恰当性评估。在人工标注的测试集上实验表明,CEAEval-M显著优于现有语音评估和分析系统。

英文摘要:

Evaluating expressive speech remains challenging, as existing methods mainly assess emotional intensity and overlook whether a speech sample is expressively appropriate for its contextual setting. This limitation hinders reliable evaluation of speech systems used in narrative-driven and interactive applications, such as audiobooks and conversational agents. We introduce CEAEval, a Context-rich framework for Evaluating Expressive Appropriateness in speech, which assesses whether a speech sample expressively aligns with the underlying communicative intent implied by its discourse-level narrative context. To support this task, we construct CEAEval-D, the first context-rich speech dataset with real human performances in Mandarin conversational speech, providing narrative descriptions together with fifteen dimensions of human annotations covering expressive attributes and expressive appropriateness. We further develop CEAEval-M, a model that integrates knowledge distillation, planner-based multi-model collaboration, adaptive audio attention bias, and reinforcement learning to perform context-rich expressive appropriateness evaluation. Experiments on a human-annotated test set demonstrate that CEAEval-M substantially outperforms existing speech evaluation and analysis systems.

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。

↑