用扩散模型生成音频，能分离声源、模拟音效、调参数。
Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond
- 用文本引导的音频扩散模型，通过蒸馏生成先验知识。
- 单个预训练模型完成音效模拟、参数校准和声源分离。
- 适合想用生成模型做音频处理的研究者和开发者。
我们提出Audio-SDS，将得分蒸馏采样（Score Distillation Sampling, SDS）扩展至文本条件音频扩散模型。尽管SDS最初用于文本到3D生成，其核心思想——将强大生成先验蒸馏为独立参数化表示——可推广至音频领域。借助单一预训练模型，Audio-SDS无需专用数据集即可实现多种任务：指导物理启发的撞击声模拟、校准FM合成参数、执行提示指定的声源分离。结果表明，基于蒸馏的方法在多模态中具有高度通用性，为未来利用生成先验解决音频任务奠定坚实基础。
原文摘要 · Abstract (English)
We introduce Audio-SDS, a generalization of Score Distillation Sampling (SDS) to text-conditioned audio diffusion models. While SDS was initially designed for text-to-3D generation using image diffusion, its core idea of distilling a powerful generative prior into a separate parametric representation extends to the audio domain. Leveraging a single pretrained model, Audio-SDS enables a broad range of tasks without requiring specialized datasets. In particular, we demonstrate how Audio-SDS can guide physically informed impact sound simulations, calibrate FM-synthesis parameters, and perform prompt-specified source separation. Our findings illustrate the versatility of distillation-based methods across modalities and establish a robust foundation for future work using generative priors in audio tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。