Abstract
Current emotional text-to-speech tasks have achieved high-quality emotional speech by incorporating emotion modules into text-to-speech models. However, there has been limited in-depth research on embedding emotion modules within TTS models, and the expression of emotion in synthesized speech is constrained by both the TTS model and the emotion module, often preventing optimal results. This paper presents a novel TTS model, Grad-DiT, based on the DiT architecture of diffusion models, aimed at enhancing the naturalness and expressiveness of TTS. Unlike traditional U-net architectures, Grad-DiT leverages the Transformer architecture to better capture contextual information in text, resulting in more natural speech generation. Building on this model, we propose Emo-DiT, which incorporates an Emotion Feature Reconstruction (EFR) module to enable the synthesis of speech with specific emotional expressions. Experimental results show that Grad-DiT not only surpasses existing TTS models in speech quality but also significantly improves real-time performance and inference speed. Compared to traditional emotion generation methods, Emo-DiT offers more precise emotional expression, enabling the synthesis of speech with distinctive emotional characteristics and providing substantial support for future applications in emotional speech synthesis.
Funding Information
  • National Natural Science Foundation of China (62371144)
  • National Natural Science Foundation of China (62461004)
  • National Natural Science Foundation of China (62172458)