LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916283712274432 |
|---|---|
| author | Guan, Wenhao Wang, Kaidi Zhou, Wangjin Wang, Yang Deng, Feng Wang, Hui Li, Lin Hong, Qingyang Qin, Yong |
| author_facet | Guan, Wenhao Wang, Kaidi Zhou, Wangjin Wang, Yang Deng, Feng Wang, Hui Li, Lin Hong, Qingyang Qin, Yong |
| contents | Recently, the application of diffusion models has facilitated the significant development of speech and audio generation. Nevertheless, the quality of samples generated by diffusion models still needs improvement. And the effectiveness of the method is accompanied by the extensive number of sampling steps, leading to an extended synthesis time necessary for generating high-quality audio. Previous Text-to-Audio (TTA) methods mostly used diffusion models in the latent space for audio generation. In this paper, we explore the integration of the Flow Matching (FM) model into the audio latent space for audio generation. The FM is an alternative simulation-free method that trains continuous normalization flows (CNF) based on regressing vector fields. We demonstrate that our model significantly enhances the quality of generated audio samples, achieving better performance than prior models. Moreover, it reduces the number of inference steps to ten steps almost without sacrificing performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08203 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation Guan, Wenhao Wang, Kaidi Zhou, Wangjin Wang, Yang Deng, Feng Wang, Hui Li, Lin Hong, Qingyang Qin, Yong Audio and Speech Processing Sound Recently, the application of diffusion models has facilitated the significant development of speech and audio generation. Nevertheless, the quality of samples generated by diffusion models still needs improvement. And the effectiveness of the method is accompanied by the extensive number of sampling steps, leading to an extended synthesis time necessary for generating high-quality audio. Previous Text-to-Audio (TTA) methods mostly used diffusion models in the latent space for audio generation. In this paper, we explore the integration of the Flow Matching (FM) model into the audio latent space for audio generation. The FM is an alternative simulation-free method that trains continuous normalization flows (CNF) based on regressing vector fields. We demonstrate that our model significantly enhances the quality of generated audio samples, achieving better performance than prior models. Moreover, it reduces the number of inference steps to ten steps almost without sacrificing performance. |
| title | LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2406.08203 |