Although Shannon theory states that it is asymptotically optimal to separate the source and
channel coding as two independent processes, in many practical communication scenarios …

For reliable transmission across a noisy communication channel, classical results from
information theory show that it is asymptotically optimal to separate out the source and …

The joint source-channel coding (JSCC) framework leverages deep learning to learn from
data the best codes for source and channel coding. When the output signal, rather than …

For reliable transmission across a noisy communication channel, classical results from
information theory show that it is asymptotically optimal to separate out the source and …

Multi-task learning (MTL) is an efficient way to improve the performance of related tasks by
sharing knowledge. However, most existing MTL networks run on a single end and are not …

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 …

As one of the key techniques to realize semantic communications, end-to-end optimized
neural joint source-channel coding (JSCC) has made great progress over the past few …

We consider the design of neural network based joint source channel coding (JSCC)
schemes for transmitting an independent and identically distributed (iid) Gaussian source …

Recently deep neural networks have been successfully applied in channel coding to
improve the decoding performance. However, the state-of-the-art neural channel decoders …

In this paper, we propose a deep neural network framework for Joint Source-Channel
Coding of an m dimensional iid Gaussian source for transmission over a single additive …