DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles
Jiaxuan Liu, Zhaoci Liu, Yajun Hu, Yingying Gao, Shilei Zhang, Zhenhua Ling
Abstract
Human speech exhibits rich and flexible prosodic variations. To address the one-to-many mapping problem from text to prosody in a reasonable and flexible manner, we propose DiffStyleTTS, a multi-speaker acoustic model based on a conditional diffusion module and an improved classifier-free guidance, which hierarchically models speech prosodic features, and controls different prosodic styles to guide prosody prediction. Experiments show that our method outperforms all baselines in naturalness and achieves superior synthesis speed compared to three diffusion-based baselines. Additionally, by adjusting the guiding scale, DiffStyleTTS effectively controls the guidance intensity of the synthetic prosody.
BibTeX
@inproceedings{liu-etal-2025-diffstyletts,
title = "{D}iff{S}tyle{TTS}: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles",
author = "Liu, Jiaxuan and
Liu, Zhaoci and
Hu, Yajun and
Gao, Yingying and
Zhang, Shilei and
Ling, Zhenhua",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.352/",
pages = "5265--5272"
}