Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-Speech
This paper proposes Emo-LiPO, a listwise preference optimization framework for LLM-based TTS to improve emotion intensity control and controllability.
The paper introduces a novel listwise preference optimization framework, Emo-LiPO, to improve emotion intensity control in LLM-based TTS systems.
Before reading this…
Applications
- →Speech synthesis
- →Emotion recognition
To understand this paper, make sure you know these concepts first:
- Large language modelsfind papers →
- Text-to-speech systemsfind papers →
Abstract
More Like ThisLarge 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.