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 2302.09174cs.LG
收藏

基于迭代源纠错的深度联合信源-信道编码

Deep Joint Source-Channel Coding with Iterative Source Error Correction

University of Michigan(密歇根大学)

Changwoo Lee, Xiao Hu, Hun-Seok Kim

摘要:

本文提出了一种基于深度学习的联合信源-信道编码(Deep JSCC)的迭代信源纠错(ISEC)解码方案。给定通过信道接收的噪声码字,我们使用深度JSCC编码器和解码器对迭代地更新码字以找到(修改的)最大后验(MAP)解决方案。为了有效的MAP解码,我们利用一个基于神经网络的去噪器来近似码字空间的对数先验密度的梯度。尽管优化问题的非凸性,我们提出的方案从传统的单次(非迭代)深度JSCC解码基线改进了各种失真和感知质量指标。此外,该方案产生更可靠的源重建结果相比,基线时的信道噪声特性不匹配的训练过程中使用的。

英文摘要:

In this paper, we propose an iterative source error correction (ISEC) decoding scheme for deep-learning-based joint source-channel coding (Deep JSCC). Given a noisy codeword received through the channel, we use a Deep JSCC encoder and decoder pair to update the codeword iteratively to find a (modified) maximum a-posteriori (MAP) solution. For efficient MAP decoding, we utilize a neural network-based denoiser to approximate the gradient of the log-prior density of the codeword space. Albeit the non-convexity of the optimization problem, our proposed scheme improves various distortion and perceptual quality metrics from the conventional one-shot (non-iterative) Deep JSCC decoding baseline. Furthermore, the proposed scheme produces more reliable source reconstruction results compared to the baseline when the channel noise characteristics do not match the ones used during training.

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。

↑