ReFlow-TTS: A Rectified Flow Model for High-fidelity Text-to-Speech

TL;DR

ReFlow-TTS introduces a rectified flow-based method for high-fidelity speech synthesis that achieves high-quality results with a single sampling step, significantly reducing synthesis time compared to traditional diffusion models.

Contribution

It presents a novel rectified flow approach for TTS that eliminates the need for multiple sampling steps and teacher models, enabling efficient high-quality speech synthesis.

Findings

ReFlow-TTS outperforms other diffusion-based models on LJSpeech.

Single-step ReFlow-TTS achieves competitive performance with existing one-step TTS models.

The method transports Gaussian to Mel-spectrogram distribution via straight line paths.

Abstract

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.