DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles
Liu, Jiaxuan, Liu, Zhaoci, Hu, Yajun, Gao, Yingying, Zhang, Shilei, Ling, Zhenhua
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Dec-4-2024
- Genre:
- Research Report (1.00)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning (1.00)
- Speech > Speech Synthesis (0.52)
- Vision > Optical Character Recognition (0.41)
- Information Technology > Artificial Intelligence