Deep Joint Source-Channel Coding with Iterative Source Error Correction
This work addresses incremental improvements in communication systems for applications requiring robust data transmission, such as multimedia streaming or wireless networks.
The paper tackles the problem of improving joint source-channel coding by proposing an iterative source error correction scheme that updates noisy codewords to approximate a maximum a-posteriori solution, resulting in enhanced distortion and perceptual quality metrics compared to non-iterative baselines and more reliable reconstructions under mismatched channel noise conditions.
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.