DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training
This work addresses the need for faster and more efficient prosody generation in speech synthesis systems, representing an incremental improvement over existing methods.
The paper tackles the problem of slow inference and long-term dependency in expressive text-to-speech synthesis by proposing DiffProsody, a diffusion-based latent prosody generator with prosody conditional adversarial training, which generates prosody 16 times faster than conventional diffusion models.
Expressive text-to-speech systems have undergone significant advancements owing to prosody modeling, but conventional methods can still be improved. Traditional approaches have relied on the autoregressive method to predict the quantized prosody vector; however, it suffers from the issues of long-term dependency and slow inference. This study proposes a novel approach called DiffProsody in which expressive speech is synthesized using a diffusion-based latent prosody generator and prosody conditional adversarial training. Our findings confirm the effectiveness of our prosody generator in generating a prosody vector. Furthermore, our prosody conditional discriminator significantly improves the quality of the generated speech by accurately emulating prosody. We use denoising diffusion generative adversarial networks to improve the prosody generation speed. Consequently, DiffProsody is capable of generating prosody 16 times faster than the conventional diffusion model. The superior performance of our proposed method has been demonstrated via experiments.