ReFlow-TTS: A Rectified Flow Model for High-fidelity Text-to-Speech
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913216540442624 |
|---|---|
| author | Guan, Wenhao Su, Qi Zhou, Haodong Miao, Shiyu Xie, Xingjia Li, Lin Hong, Qingyang |
| author_facet | Guan, Wenhao Su, Qi Zhou, Haodong Miao, Shiyu Xie, Xingjia Li, Lin Hong, Qingyang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_17056 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | ReFlow-TTS: A Rectified Flow Model for High-fidelity Text-to-Speech Guan, Wenhao Su, Qi Zhou, Haodong Miao, Shiyu Xie, Xingjia Li, Lin Hong, Qingyang Sound Audio and Speech Processing 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. |
| title | ReFlow-TTS: A Rectified Flow Model for High-fidelity Text-to-Speech |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2309.17056 |