Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models

1Zhejiang University 2Peking University 3Speech & Audio Team, ByteDance AI Lab *Equal Contribution Abstract Large-scale multimodal generative modeling has created milestones in text-to-image and text-to-video generation. Its application to audio still lags behind due to two main reasons: the lack of large-scale datasets with high-quality text-audio pairs, and the complexity of modeling long contin