The diffusion models including Denoising Diffusion Probabilistic Models (DDPM) and score-based generative models have demonstrated excellent performance in speech synthesis tasks. However, its effectiveness comes at the cost of numerous sampling steps, resulting in prolonged sampling time required to synthesize high-quality speech. This drawback hinders its practical applicability in real-world scenarios. In this paper, we introduce ReFlow-TTS, a novel rectified flow based method for speech synthesis with high-fidelity. Specifically, our ReFlow-TTS is simply an Ordinary Differential Equation (ODE) model that transports Gaussian distribution to the ground-truth Mel-spectrogram distribution by straight line paths as much as possible. Furthermore, our proposed approach enables high-quality speech synthesis with a single sampling step and eliminates the need for training a teacher model. Our experiments on LJSpeech Dataset show that our ReFlow-TTS method achieves the best performance compared with other diffusion based models. And the ReFlow-TTS with one step sampling achieves competitive performance compared with existing one-step TTS models.

翻译：扩散模型，包括去噪扩散概率模型（DDPM）和基于分数的生成模型，已在语音合成任务中展现出卓越性能。然而，其有效性以大量采样步骤为代价，导致合成高质量语音所需的采样时间过长。这一缺陷阻碍了其在实际场景中的实用价值。本文提出ReFlow-TTS，一种基于整流流的新型高保真语音合成方法。具体而言，我们的ReFlow-TTS本质上是一个常微分方程（ODE）模型，通过尽可能直线路径将高斯分布输送到真实梅尔频谱分布。此外，所提方法能够以单步采样实现高质量语音合成，且无需训练教师模型。在LJSpeech数据集上的实验表明，我们的ReFlow-TTS方法相较于其他基于扩散的模型取得了最优性能。同时，单步采样的ReFlow-TTS与现有单步TTS模型相比，性能具有竞争力。