Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.07776 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918021917835264 |
|---|---|
| author | Wang, Kaidi Guan, Wenhao Lu, Shenghui Yao, Jianglong Li, Lin Hong, Qingyang |
| author_facet | Wang, Kaidi Guan, Wenhao Lu, Shenghui Yao, Jianglong Li, Lin Hong, Qingyang |
| contents | Recently, flow matching based speech synthesis has significantly enhanced the quality of synthesized speech while reducing the number of inference steps. In this paper, we introduce SlimSpeech, a lightweight and efficient speech synthesis system based on rectified flow. We have built upon the existing speech synthesis method utilizing the rectified flow model, modifying its structure to reduce parameters and serve as a teacher model. By refining the reflow operation, we directly derive a smaller model with a more straight sampling trajectory from the larger model, while utilizing distillation techniques to further enhance the model performance. Experimental results demonstrate that our proposed method, with significantly reduced model parameters, achieves comparable performance to larger models through one-step sampling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07776 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SlimSpeech: Lightweight and Efficient Text-to-Speech with Slim Rectified Flow Wang, Kaidi Guan, Wenhao Lu, Shenghui Yao, Jianglong Li, Lin Hong, Qingyang Sound Artificial Intelligence Recently, flow matching based speech synthesis has significantly enhanced the quality of synthesized speech while reducing the number of inference steps. In this paper, we introduce SlimSpeech, a lightweight and efficient speech synthesis system based on rectified flow. We have built upon the existing speech synthesis method utilizing the rectified flow model, modifying its structure to reduce parameters and serve as a teacher model. By refining the reflow operation, we directly derive a smaller model with a more straight sampling trajectory from the larger model, while utilizing distillation techniques to further enhance the model performance. Experimental results demonstrate that our proposed method, with significantly reduced model parameters, achieves comparable performance to larger models through one-step sampling. |
| title | SlimSpeech: Lightweight and Efficient Text-to-Speech with Slim Rectified Flow |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2504.07776 |