Emotion-Aligned Generation in Diffusion Text to Speech Models via Preference-Guided Optimization
Year: 2025
Type: preprint
Abstract: Emotional text-to-speech seeks to convey affect while preserving intelligibility and prosody, yet existing methods rely on coarse labels or proxy classifiers and receive only utterance-level feedback. We introduce Emotion-Aware Stepwise Preference Optimization (EASPO), a post-training framework that aligns diffusion TTS with fine-grained emotional preferences at intermediate denoising steps. Central to our approach is EASPM, a time-conditioned model that scores noisy intermediate speech states and enables automatic preference pair construction. EASPO optimizes generation to match these stepwise preferences, enabling controllable emotional shaping. Experiments show superior performance over existing methods in both expressiveness and naturalness.
Source: arXiv (Cornell University)
Authors: Shi, Jiacheng, Du, Hongfei, He, Yangfan, Hong, Y. Alicia, Gao, Ye
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7084626089
Cites:
Cited by:
Related to: