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 2104.07161cs.SDcs.LGeess.AS
收藏

用于无监督音频恢复的深度先验设计

On the Design of Deep Priors for Unsupervised Audio Restoration

Arizona State University(亚利桑那州立大学);Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室)

Vivek Sivaraman Narayanaswamy, Jayaraman J. Thiagarajan, Andreas Spanias

摘要:

用于解决音频恢复问题的无监督深度学习方法广泛依赖于精心定制的神经架构,这些神经架构携带用于在时域或谱域中定义先验的强归纳偏差。在这种情况下,最近已经通过复杂的卷积网络结构在频谱域中恢复音频信号取得了很多成功。然而,在实践中,音频先验需要对卷积核进行仔细的工程设计,以有效地解决不适定的恢复任务,同时还易于训练。为此,在本文中,我们提出了一种新的基于U-Net的先验,它不会影响现有卷积架构的网络复杂性或收敛行为,但会显著改善恢复。特别是,我们提倡使用精心设计的膨胀时间表和密集连接的U-Net架构,以获得强大的音频先验。使用标准基准和各种不适定的恢复任务,如音频去噪,在绘画和声源分离的实证研究,我们证明,我们提出的方法始终优于广泛采用的音频先验架构。

英文摘要:

Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for defining priors in the time or spectral domain. In this context, lot of recent success has been achieved with sophisticated convolutional network constructions that recover audio signals in the spectral domain. However, in practice, audio priors require careful engineering of the convolutional kernels to be effective at solving ill-posed restoration tasks, while also being easy to train. To this end, in this paper, we propose a new U-Net based prior that does not impact either the network complexity or convergence behavior of existing convolutional architectures, yet leads to significantly improved restoration. In particular, we advocate the use of carefully designed dilation schedules and dense connections in the U-Net architecture to obtain powerful audio priors. Using empirical studies on standard benchmarks and a variety of ill-posed restoration tasks, such as audio denoising, in-painting and source separation, we demonstrate that our proposed approach consistently outperforms widely adopted audio prior architectures.

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。

↑