Saved in:
Bibliographic Details
Main Authors: Niu, Xinlei, Zhang, Jing, Walder, Christian, Martin, Charles Patrick
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