CommentsAccepted for publication in 18th International Conference on Sustainability in Energy and Buildings (SEB-26), to appear in Springer Nature proceedings (KES Smart Innovation Systems and Technologies). The final authenticated version will be available online at Springer
Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-Speech
Emo-LiPO:基于LLM的文本到语音中细粒度情感强度控制的列表式偏好优化
Yihang Lin, Li Zhou, Congwei Cao, Dongchu Xie, Xiaoxue Gao, Chen Zhang, Haizhou Li
机构
*
The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))
;
Agency for Science, Technology and Research(新加坡科技研究局)
;
National University of Singapore(新加坡国立大学)
;
Shenzhen Research Institute of Big Data(深圳市大数据研究院)
;
Shenzhen Loop Area Institute(深圳河套学院)
专题命中
后训练与偏好优化
:LLM(title,title_cn);preference optimization(title,abstract);large language model(abstract);language model(abstract)
CommentsThis paper contains 12 pages, 7 figures. This is an original unpublished manuscript submitted to the arXiv preprint server, with no prior publication or conference presentation
CommentsPlease cite the definitive, peer-reviewed version of this article published in the Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, edited by Christos Christodoulopoulos et al., Association for Computational Linguistics, pp. 10007-10030, 2025. DOI: https://doi.org/10.18653/v1/2025.emnlp-main.507
Journal refProceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, pp. 10007-10030, 2025