Text-to-audio (TTA) system has recently gained attention for its ability to synthesize general audio based on text descriptions. However, previous studies in TTA have limited generation quality with high computational costs. In this study, we propose AudioLDM, a TTA system that is built on a latent space to learn the continuous audio representations from contrastive language-audio pretraining (CLAP) latents. The pretrained CLAP models enable us to train LDMs with audio embedding while providing text embedding as a condition during sampling. By learning the latent representations of audio signals and their compositions without modeling the cross-modal relationship, AudioLDM is advantageous in both generation quality and computational efficiency. Trained on AudioCaps with a single GPU, AudioLDM achieves state-of-the-art TTA performance measured by both objective and subjective metrics (e.g., frechet distance). Moreover, AudioLDM is the first TTA system that enables various text-guided audio manipulations (e.g., style transfer) in a zero-shot fashion. Our implementation and demos are available at https://audioldm.github.io.

翻译：文本到音频（TTA）系统因其基于文本描述合成通用音频的能力近期备受关注。然而，现有TTA研究存在生成质量有限且计算成本高昂的问题。本研究提出AudioLDM，一种构建于潜在空间的TTA系统，该系统从对比语言-音频预训练（CLAP）的潜在表示中学习连续音频表征。预训练的CLAP模型使我们能够使用音频嵌入训练潜在扩散模型（LDM），同时在采样阶段将文本嵌入作为条件输入。通过学习音频信号及其组合的潜在表示，而无需建模跨模态关系，AudioLDM在生成质量和计算效率方面均具有优势。在单GPU环境下基于AudioCaps数据集训练的AudioLDM，在客观与主观指标（如弗雷歇距离）上均达到最先进的TTA性能。此外，AudioLDM是首个支持零样本文本引导音频操作（如风格迁移）的TTA系统。我们的实现与演示请见https://audioldm.github.io。