Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.15338 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911885940490240 |
|---|---|
| author | Niu, Xinlei Zhang, Jing Walder, Christian Martin, Charles Patrick |
| author_facet | Niu, Xinlei Zhang, Jing Walder, Christian Martin, Charles Patrick |
| contents | We present SoundLoCD, a novel text-to-sound generation framework, which incorporates a LoRA-based conditional discrete contrastive latent diffusion model. Unlike recent large-scale sound generation models, our model can be efficiently trained under limited computational resources. The integration of a contrastive learning strategy further enhances the connection between text conditions and the generated outputs, resulting in coherent and high-fidelity performance. Our experiments demonstrate that SoundLoCD outperforms the baseline with greatly reduced computational resources. A comprehensive ablation study further validates the contribution of each component within SoundLoCD. Demo page: \url{https://XinleiNIU.github.io/demo-SoundLoCD/}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_15338 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SoundLoCD: An Efficient Conditional Discrete Contrastive Latent Diffusion Model for Text-to-Sound Generation Niu, Xinlei Zhang, Jing Walder, Christian Martin, Charles Patrick Sound Audio and Speech Processing We present SoundLoCD, a novel text-to-sound generation framework, which incorporates a LoRA-based conditional discrete contrastive latent diffusion model. Unlike recent large-scale sound generation models, our model can be efficiently trained under limited computational resources. The integration of a contrastive learning strategy further enhances the connection between text conditions and the generated outputs, resulting in coherent and high-fidelity performance. Our experiments demonstrate that SoundLoCD outperforms the baseline with greatly reduced computational resources. A comprehensive ablation study further validates the contribution of each component within SoundLoCD. Demo page: \url{https://XinleiNIU.github.io/demo-SoundLoCD/}. |
| title | SoundLoCD: An Efficient Conditional Discrete Contrastive Latent Diffusion Model for Text-to-Sound Generation |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2405.15338 |