arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.15140cs.SDeess.AS
收藏

通过显式建模源之间的相关性来改进声源分离

Improving Source Separation by Explicitly Modeling Dependencies Between Sources

Google(谷歌)

Ethan Manilow, Curtis Hawthorne, Cheng-Zhi Anna Huang, Bryan Pardo, Jesse Engel

摘要:

我们提出了一种新的方法来训练监督声源分离系统,其目的是学习混合物中所有源组合之间的相互依赖关系。我们不是从混合中独立地估计每个源,而是将声源分离问题重构为无顺序神经自回归密度估计(NADE),并从混合和其他源的随机子集中估计每个源。我们采用了一个标准的声源分离架构,Demucs,除了输入混合物外,还为每个单独的源提供了额外的输入。我们在训练过程中随机屏蔽这些输入源,以便网络学习源之间的条件依赖关系。通过将这种训练方法与推理时的块Gibbs采样过程配对,我们证明了网络可以通过将源估计条件化到其早期源估计来迭代地提高其分离性能。在两个声源分离数据集上的实验表明,使用无顺序NADE方法并在推理时使用Gibbs采样(多达512步)训练Demucs模型的性能明显优于使用标准回归损失和直接(一步)估计源的Demucs基线。

英文摘要:

We propose a new method for training a supervised source separation system that aims to learn the interdependent relationships between all combinations of sources in a mixture. Rather than independently estimating each source from a mix, we reframe the source separation problem as an Orderless Neural Autoregressive Density Estimator (NADE), and estimate each source from both the mix and a random subset of the other sources. We adapt a standard source separation architecture, Demucs, with additional inputs for each individual source, in addition to the input mixture. We randomly mask these input sources during training so that the network learns the conditional dependencies between the sources. By pairing this training method with a block Gibbs sampling procedure at inference time, we demonstrate that the network can iteratively improve its separation performance by conditioning a source estimate on its earlier source estimates. Experiments on two source separation datasets show that training a Demucs model with an Orderless NADE approach and using Gibbs sampling (up to 512 steps) at inference time strongly outperforms a Demucs baseline that uses a standard regression loss and direct (one step) estimation of sources.

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。

↑