DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles

TL;DR

DiffStyleTTS introduces a diffusion-based hierarchical model for multi-style text-to-speech synthesis, enabling flexible prosody control, improved naturalness, and faster synthesis compared to existing diffusion models.

Contribution

It presents a novel hierarchical diffusion model with enhanced prosody control and guidance mechanisms for more natural and diverse speech synthesis.

Findings

Outperforms baselines in naturalness

Achieves faster synthesis speed

Effectively controls prosody guidance intensity

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.