Preprint
Sep 2026
Post-Training Zero-Shot TTS for Fine-Grained Emotion and Duration Control via Natural Language
A unified post-training framework that equips pretrained text-to-speech models with natural-language control over segment-level emotion and duration is proposed, highlighting post-training as a practical approach to extending existing speech synthesis models.
Lian-Ru Gao, Yu-Jie Guo, Yong Qin
· 0 citations