---
title: "Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-Speech"
authors:
  - "Yihang Lin"
  - "Li Zhou"
  - "Congwei Cao"
  - "Dongchu Xie"
  - "Xiaoxue Gao"
  - "Chen Zhang"
  - "Haizhou Li"
doi: "10.24963/ijcai.2026/652"
url: "https://ijcai.org/proceedings/2026/652"
pdf: "https://ijcai.org/proceedings/2026/0652.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "5855-5863"
track: "Main Track"
keywords:
  - "Natural Language Processing: Speech"
---

# Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-Speech

Yihang Lin, Li Zhou, Congwei Cao, Dongchu Xie, Xiaoxue Gao, Chen Zhang, Haizhou Li

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 5855-5863. DOI: [10.24963/ijcai.2026/652](https://doi.org/10.24963/ijcai.2026/652)

## 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.