We demonstrate how conditional generation from diffusion models can be used to tackle a variety of realistic tasks in the production of music in 44.1kHz stereo audio with sampling-time guidance. The scenarios we consider include continuation, inpainting and regeneration of musical audio, the creation of smooth transitions between two different music tracks, and the transfer of desired stylistic characteristics to existing audio clips. We achieve this by applying guidance at sampling time in a simple framework that supports both reconstruction and classification losses, or any combination of the two. This approach ensures that generated audio can match its surrounding context, or conform to a class distribution or latent representation specified relative to any suitable pre-trained classifier or embedding model.

翻译：我们展示了如何利用扩散模型的条件生成能力，通过采样时引导技术解决44.1kHz立体声音乐制作中的多种实际任务。所探讨的场景包括音乐音频的续接、修补与再生，两段不同音乐轨道的平滑过渡，以及对现有音频片段所需风格特征的迁移。通过在统一框架下应用采样时引导（该框架支持重构损失函数、分类损失函数或两者的任意组合），本方法确保生成的音频既能匹配其上下文环境，又能符合任意预训练分类器或嵌入模型所定义的类别分布或潜在表征。