分离与扩散：使用预训练扩散模型改进源分离
Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation
AI总结：
针对语音分离任务，本文将确定性模型的上界推广至随机生成模型，提出将预训练扩散模型 Vocoder 与确定性分离模型的输出在频域内进行加权线性组合，在多基准测试中取得最先进结果并突破双说话人性能上界。
摘要：
语音分离问题，也被称为鸡尾酒会问题，是指从混合语音信号中分离出单一语音信号的任务。先前关于源分离的工作推导出了人类语音领域中源分离任务的上界。该上界是针对确定性模型推导的。生成模型的最新进展挑战了这一上界。我们展示了如何将该上界推广到随机生成模型的情况。将预训练用于建模单说话人语音的扩散模型 Vocoder 应用于确定性分离模型的输出，可以实现最先进的分离结果。研究表明，这需要将分离模型的输出与扩散模型的输出相结合。在我们的方法中，在频域内执行线性组合，使用由学习模型推断出的权重。我们在多个基准上的 2、3、5、10 和 20 个说话人场景中展示了最先进的结果。特别是，对于两个说话人，我们的方法能够超越先前被认为是性能上界的水平。
英文摘要：
The problem of speech separation, also known as the cocktail party problem, refers to the task of isolating a single speech signal from a mixture of speech signals. Previous work on source separation derived an upper bound for the source separation task in the domain of human speech. This bound is derived for deterministic models. Recent advancements in generative models challenge this bound. We show how the upper bound can be generalized to the case of random generative models. Applying a diffusion model Vocoder that was pretrained to model single-speaker voices on the output of a deterministic separation model leads to state-of-the-art separation results. It is shown that this requires one to combine the output of the separation model with that of the diffusion model. In our method, a linear combination is performed, in the frequency domain, using weights that are inferred by a learned model. We show state-of-the-art results on 2, 3, 5, 10, and 20 speakers on multiple benchmarks. In particular, for two speakers, our method is able to surpass what was previously considered the upper performance bound.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
