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 1906.07552eess.AScs.LGcs.SDstat.ML
收藏

基于生成对抗网络的单通道信号分离与反卷积

Single-Channel Signal Separation and Deconvolution with Generative Adversarial Networks

University of Surrey(萨里大学);Tencent AI lab(腾讯人工智能实验室)

Qiuqiang Kong, Yong Xu, Wenwu Wang, Philip J. B. Jackson, Mark D. Plumbley

摘要:

单通道信号分离和反卷积的目的是从单通道混合信号中分离和反卷积单个信号源,这是一个具有挑战性的问题,其中没有混合滤波器的先验知识。单个源和混合滤波器都需要估计。此外,混合物可能包含在训练集中看不到的非平稳噪声。本文提出了一种合成-分解(S-D)方法来解决单通道分离和反卷积问题。在合成中,使用生成对抗网络(GAN)构建源的生成模型。在分解中,混合滤波器和源都被优化以最小化混合的重构误差。所提出的S-D方法在图像修复和完成中实现了18.9 dB和15.4 dB的峰值噪声比(PSNR),分别优于15.3 dB和12.2 dB的基线卷积神经网络PSNR,并且在源分离和反卷积中实现了13.2 dB的PSNR,优于10.1dB的卷积非负矩阵分解(NMF)基线。

英文摘要:

Single-channel signal separation and deconvolution aims to separate and deconvolve individual sources from a single-channel mixture and is a challenging problem in which no prior knowledge of the mixing filters is available. Both individual sources and mixing filters need to be estimated. In addition, a mixture may contain non-stationary noise which is unseen in the training set. We propose a synthesizing-decomposition (S-D) approach to solve the single-channel separation and deconvolution problem. In synthesizing, a generative model for sources is built using a generative adversarial network (GAN). In decomposition, both mixing filters and sources are optimized to minimize the reconstruction error of the mixture. The proposed S-D approach achieves a peak-to-noise-ratio (PSNR) of 18.9 dB and 15.4 dB in image inpainting and completion, outperforming a baseline convolutional neural network PSNR of 15.3 dB and 12.2 dB, respectively and achieves a PSNR of 13.2 dB in source separation together with deconvolution, outperforming a convolutive non-negative matrix factorization (NMF) baseline of 10.1 dB.

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。

↑