{"type":"ScholarlyArticle","title":"Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-Speech","authors":[{"name":"Yihang Lin","slug":"yihang-lin","given":"Yihang","family":"Lin","affiliation":""},{"name":"Li Zhou","slug":"li-zhou","given":"Li","family":"Zhou","affiliation":""},{"name":"Congwei Cao","slug":"congwei-cao","given":"Congwei","family":"Cao","affiliation":""},{"name":"Dongchu Xie","slug":"dongchu-xie","given":"Dongchu","family":"Xie","affiliation":""},{"name":"Xiaoxue Gao","slug":"xiaoxue-gao","given":"Xiaoxue","family":"Gao","affiliation":""},{"name":"Chen Zhang","slug":"chen-zhang","given":"Chen","family":"Zhang","affiliation":""},{"name":"Haizhou Li","slug":"haizhou-li","given":"Haizhou","family":"Li","affiliation":""}],"abstract":"Large language model (LLM)-based text-to-speech (TTS) systems enable prompt-conditioned emotional control but struggle with fine-grained emotion intensity due to the semantic--acoustic gap between text and speech. To address this challenge, we formulate emotion intensity control in LLM-based TTS as a learning-to-rank problem and propose Emo-LiPO, a listwise preference optimization framework that aligns prompt-conditioned speech generation with relative emotion intensity expressed in text. Emo-LiPO explicitly models global intensity ordering within each emotion under fixed transcripts, enabling more faithful and continuous emotional expression. We further construct ESD-plus, a multi-speaker dataset with explicit emotion intensity variations, to support fine-grained emotion modeling and evaluation. Experiments on ESD-plus demonstrate that Emo-LiPO significantly improves emotion accuracy and intensity controllability over both supervised- and DPO-based LLM TTS baselines, with particularly pronounced gains at high intensity levels.","doi":"10.24963/ijcai.2026/652","url":"https://ijcai.org/proceedings/2026/652","pdf":"https://ijcai.org/proceedings/2026/0652.pdf","markdown":"https://ijcai.org/proceedings/2026/652.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/652","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Natural Language Processing","track":"Main Track","number":652,"pages":{"first":5855,"last":5863},"keywords":["Natural Language Processing: Speech"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}