Deep Joint Source-Channel Coding with Iterative Source Error Correction

Changwoo Lee, Xiao Hu, Hun-Seok Kim
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:3879-3902, 2023.

Abstract

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v206-lee23c, title = {Deep Joint Source-Channel Coding with Iterative Source Error Correction}, author = {Lee, Changwoo and Hu, Xiao and Kim, Hun-Seok}, booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics}, pages = {3879--3902}, year = {2023}, editor = {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem}, volume = {206}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v206/lee23c/lee23c.pdf}, url = {https://proceedings.mlr.press/v206/lee23c.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Deep Joint Source-Channel Coding with Iterative Source Error Correction %A Changwoo Lee %A Xiao Hu %A Hun-Seok Kim %B Proceedings of The 26th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2023 %E Francisco Ruiz %E Jennifer Dy %E Jan-Willem van de Meent %F pmlr-v206-lee23c %I PMLR %P 3879--3902 %U https://proceedings.mlr.press/v206/lee23c.html %V 206 %X 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.
APA
Lee, C., Hu, X. & Kim, H.. (2023). Deep Joint Source-Channel Coding with Iterative Source Error Correction. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 206:3879-3902 Available from https://proceedings.mlr.press/v206/lee23c.html.

Related Material