Joint Source-channel Coding Research Articles

Deep Joint Source-Channel Coding for CSI Feedback: An End-to-End Approach

The increased throughput brought by MIMO technology relies on the knowledge of channel state information (CSI) acquired in the base station (BS). To make the CSI feedback overhead affordable for the evolution of MIMO technology (e.g., massive MIMO and ultra-massive MIMO), deep learning (DL) is introduced to deal with the CSI compression task. In traditional communication systems, the compressed CSI bits is treated equally and expected to be transmitted accurately over the noisy channel. While the errors occur due to the limited bandwidth or low signal-to-noise ratios (SNRs), the reconstruction performance of the CSI degrades drastically. As a branch of semantic communications, deep joint source-channel coding (DJSCC) scheme performs better than the separate source-channel coding (SSCC) scheme—the cornerstone of traditional communication systems—in the limited bandwidth and low SNRs. In this paper, we propose a DJSCC based framework for the CSI feedback task. In particular, the proposed method can simultaneously learn from the CSI source and the wireless channel. Instead of truncating CSI via Fourier transform in the delay domain in existing methods, we apply non-linear transform networks to compress the CSI. Furthermore, we adopt an SNR adaption mechanism to deal with wireless channel variations. The extensive experiments demonstrate the validity, adaptability, and generality of the proposed framework.

Neural joint source-channel coding via Bernoulli latent straight-through estimator

Under infinite block length, from Shannon's separation theorem, it is well-known that by independent design of source coding and channel coding, the optimal throughput — the channel capacity — can be reached with careful design of the corresponding functionalities. However, when restricted to finite block length, the separation theorem does not necessarily hold, and hence joint source-channel coding (JSCC) theorem has been raised as an alternative strategy for achieving the capacity of the channel. However, as JSCC formulates highly non-convex problem which cannot be directly solved analytically, recently, deep learning has been proposed as a key enabler for JSCC. While most work on deep-learning-based JSCC focused on transmission of continuous signals through wireless channels, we focus in this paper the case of information-theoretic channel, namely binary symmetric channel, which can give useful insights on information-theoretic perspective on JSCC. Unlike recent work on deep-learning-based, or neural, JSCC for discrete channels that considered score function estimator to train the JSCC, in this paper, we improve the performance of neural JSCC by estimating the gradient more precisely as compared to the previous approach. Key idea is to consider soft codeword during training to enable path-wise gradient estimator which is proven to have lower variance than the score-function estimator. Experimental results on MNIST and CIFAR-10 datasets show that the proposed neural JSCC outperforms the previous work on JSCC for discrete channels, validating the effectiveness of the proposed gradient computation technique.

High-density analog image storage in an analog-valued non-volatile memory array

Data stored in the cloud or on mobile devices reside in physical memory systems with finite sizes. Today, huge amounts of analog data, e.g. images and videos, are first digitalized and then compression algorithms (e.g. the JPEG standard) are employed to minimize the amount of physical storage required. Emerging non-volatile-memory technologies (e.g. phase change memory (PCM), resistive RAM (RRAM)) provide the possibility to store the analog information in a compressed format directly into analog memory systems. Here, we demonstrate with hardware experiments an image storage and compression scheme (joint source-channel coding) with analog-valued PCM and RRAM arrays. This scheme stores information in a distributed fashion and shows resilience to the PCM and RRAM device technology non-idealities, including defective cells, device variability, resistance drift, and relaxation.

Semantic Coding for Text Transmission: An Iterative Design

We consider the wireless text transmission using joint source-channel coding (JSCC). Classical source coding only considers the syntactic information based on probabilistic models, ignoring the meaning of source messages. Neural network based joint source and channel coders handle the source semantic information more efficiently. However, existing semantic transmission using end-to-end neural networks do not generalize well under varying channel conditions. To tackle this, we propose a semi-neural framework with an iterative architecture, named iterative semantic JSCC (IS-JSCC). Specifically, at each iteration, the remaining semantics is extracted from the intermediate decoded text and is then used as a priori information for the channel decoder in the next iteration. Instead of reconstructing text explicitly, we synthesize the semantics of candidate words in the embedding space, weighted by their posterior probability. This soft semantic synthesis alleviates the error propagation and reduces the complexity of iterative decoding as well. Results show that compared to full-neural designs, the proposed framework can improve the quality of text reconstruction by joint iterative decoding and exhibit better robustness over wireless channels.

DeepJSCC-Q: Constellation Constrained Deep Joint Source-Channel Coding

DeepJSCC-Q: Constellation Constrained Deep Joint Source-Channel Coding

Minimum Energy Analysis for Robust Gaussian Joint Source-Channel Coding With a Distortion-Noise Profile

Minimum energy required to achieve a distortion-noise profile, i.e., a function indicating the maximum allowed distortion value for each channel noise level, is studied for transmission of Gaussian sources over Gaussian channels. A general coding scheme is proposed to upper bound the minimum energy needed for any distortion-noise profile. Conversely, utilizing a family of lower bounds originally derived for broadcast channels with power constraints, the minimum required energy is lower bounded for any profile. As examples, linear, exponential, square-law, and staircase profiles are studied. It is shown that for the linear profile, as well as for any concave profile, uncoded transmission is optimal. As a negative result, it is shown that exponential profiles are not achievable with finite energy. For square-law and staircase profiles, upper bounds and lower bounds are derived and the gaps between them are studied.

Designing a Common DP-LDPC Code Pair for Variable On-Body Channels

The joint source channel coding (JSCC) system is sensitive to the changing channel characteristics, because the optimally designed source-channel code pair always needs to be redesigned when the transmission environment is updated. A solution is to seek a common code pair for variable channels. Channel model 3 (CM3) is a variable on-body channel following the Weibull distribution, which is analyzed in four conditions due to varying shape factors, namely with exponential, Rayleigh, log-normal and normal distributions. The JSCC system is considered in this paper based on double protograph low-density parity-check (DP-LDPC) code pair over the variable CM3 channel. Firstly, four DP-LDPC code pairs are searched by the conventional differential evolution (DE) algorithm with four distributions of the Weibull model, respectively. However, these four code pairs only present good bit-error ratio performance in their own distribution, and have error floors in the other three. To resolve the problem, an artificial intelligence method based on principle component analysis (PCA) algorithm is designed to extract the common code pair. It is demonstrated that the common code pair performs well in noise-varying and practical-parameter transmissions. Instead of four DE code pairs, the designed one PCA code pair provides a strong technical support to low-complexity manufacturing such as eHealthcare.

Redesign of Channel Codes for Joint Source-Channel Coding Systems over One-Dimensional Inter-Symbol-Interference Magnetic Recording Channels

Although the joint source-channel coding (JSCC) system based on double protograph low-density parity-check (DP-LDPC) codes has been shown to possess excellent error performance over additive white Gaussian noise (AWGN) channels, it cannot perform well over one-dimensional inter-symbol-interference (OD-ISI) magnetic recording channels. In this study, a new JSCC system with a three-stage serially concatenated framework of Turbo equalization is firstly proposed for OD-ISI magnetic recording channels. Then, a modified joint protograph extrinsic information transfer (M-JPEXIT) algorithm is put forward to analyze the convergence-performance of the proposed system. By applying the M-JPEXIT algorithm, the channel codes are redesigned for this system to improve the error performance. Both the M-JPEXIT analysis and the bit-error-rate (BER) simulation results show the performance improvement of the proposed channel codes, especially in the water-fall region.

Optimizing Low-Complexity Analog Mappings for Low-Power Sensors With Energy Scheduling Capabilities

Power consumption is a major challenge for a massive deployment of wireless sensors in Internet of Things (IoT) networks. This article studies the use of analog joint source-channel coding (AJSCC) mappings in low-power sensing schemes. In particular, we propose a novel <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">triangular</i> mapping geometry as a low-complexity dimension reduction mapping. The proposed triangular mapping is employed for analog compression of multiple sensor readings into one signal and, thus, limits the need for power-hungry analog-to-digital conversion and processing at the sensing nodes. A comprehensive performance analysis of the proposed triangular mapping in terms of the mean squared error (MSE) performance is provided analytically and verified numerically. The problem of mapping adaptation to different source distributions is also studied. Moreover, the proposed triangular mapping is adopted in an energy scheduling problem in which the sensing nodes schedule their use of the received powers at different time instants and adjust the mapping parameters accordingly with the goal of minimizing the sum distortion at the receiver. We present a fast low-complexity algorithm for optimal energy scheduling and verify its performance in comparison with commercial convex optimization solvers. It is shown that the proposed mapping provides a very good MSE performance compared to the AJSCC benchmarks despite having a much lower complexity circuit implementation.

DeepWiVe: Deep-Learning-Aided Wireless Video Transmission

We present <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DeepWiVe</i> , the first-ever end-to-end joint source-channel coding (JSCC) video transmission scheme that leverages the power of deep neural networks (DNNs) to directly map video signals to channel symbols, combining video compression, channel coding, and modulation steps into a single neural transform. Our DNN decoder predicts residuals without distortion feedback, which improves the video quality by accounting for occlusion/disocclusion and camera movements. We simultaneously train different bandwidth allocation networks for the frames to allow variable bandwidth transmission. Then, we train a bandwidth allocation network using reinforcement learning (RL) that optimizes the allocation of limited available channel bandwidth among video frames to maximize the overall visual quality. Our results show that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DeepWiVe</i> can overcome the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cliff-effect</i> , which is prevalent in conventional separation-based digital communication schemes, and achieve graceful degradation with the mismatch between the estimated and actual channel qualities. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DeepWiVe</i> outperforms H.264 video compression followed by low-density parity check (LDPC) codes in all channel conditions by up to 0.0485 in terms of the multi-scale structural similarity index measure (MS-SSIM), and H.265+ LDPC by up to 0.0069 on average. We also illustrate the importance of optimizing bandwidth allocation in JSCC video transmission by showing that our optimal bandwidth allocation policy is superior to uniform allocation as well as a heuristic policy benchmark.

Energy-Limited Joint Source–Channel Coding via Analog Pulse Position Modulation

We study the problem of transmitting a source sample with minimum distortion over an infinite-bandwidth additive white Gaussian noise channel under an energy constraint. To that end, we construct a joint source–channel coding scheme using analog pulse position modulation (PPM) and bound its quadratic distortion. We show that this scheme outperforms existing techniques, since its quadratic distortion attains both the exponential and polynomial decay orders of Burnashev’s outer bound. We supplement our theoretical results with numerical simulations and comparison to existing schemes.

BER Performance Evaluation Using Deep Learning Algorithm for Joint Source Channel Coding in Wireless Networks

BER Performance Evaluation Using Deep Learning Algorithm for Joint Source Channel Coding in Wireless Networks

Nonlinear Transform Source-Channel Coding for Semantic Communications

In this paper, we propose a class of high-efficiency deep joint source-channel coding methods that can closely adapt to the source distribution under the nonlinear transform, it can be collected under the name nonlinear transform source-channel coding (NTSCC). In the considered model, the transmitter first learns a nonlinear analysis transform to map the source data into latent space, then transmits the latent representation to the receiver via deep joint source-channel coding. Our model incorporates the nonlinear transform as a strong prior to effectively extract the source semantic features and provide side information for source-channel coding. Unlike existing conventional deep joint source-channel coding methods, the proposed NTSCC essentially learns both the source latent representation and an entropy model as the prior on the latent representation. Accordingly, novel adaptive rate transmission and hyperprior-aided codec refinement mechanisms are developed to upgrade deep joint source-channel coding. The whole system design is formulated as an optimization problem whose goal is to minimize the end-to-end transmission rate-distortion performance under established perceptual quality metrics. Across test image sources with various resolutions, we find that the proposed NTSCC transmission method generally outperforms both the analog transmission using the standard deep joint source-channel coding and the classical separation-based digital transmission. Notably, the proposed NTSCC method can potentially support future semantic communications due to its content-aware ability and perceptual optimization goal.

Joint Code Rate Compatible Design of DP-LDPC Code Pairs for Joint Source Channel Coding Over Implant-to-External Channel

A CM2-S3 transmission link in wireless body area networks (WBAN) is implemented with a joint source channel coding (JSCC) system based on double protograph low-density parity-check (DP-LDPC) code pairs with high reliability and low power consumption. For the practicality and suitability considerations, the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$M$ </tex-math></inline-formula> -ary differential chaos shift keying scheme is introduced to modulate the CM2-S3 channel with better performance than the standard modulations in WBAN. Due to the non-Gaussian-like distribution of the CM2-S3 channel model, the initial joint protograph extrinsic information transfer (JPEXIT) algorithm does not work as a coding analysis tool. To solve this problem, a numerical Gaussian approximation is employed to modify the iterative mutual information function of the JPEXIT for achieving more precise output. Then, a joint code rate compatible (JCRC) method, designed with compatibility in resisting variable channel variances and adapting different source statistics, is proposed for optimizing the DP-LDPC code pairs. Based on the JCRC method, the code searching algorithm is simplified with lower complexity because of the reduced cycle-index. The simulation results show that optimized code pairs have better bit-error ratio performances compared to existing codes, which provides a strong technical support to promote high-quality data transmission in eHealthcare on the physical layer.

OFDM-Guided Deep Joint Source Channel Coding for Wireless Multipath Fading Channels

We investigate joint source channel coding (JSCC) for wireless image transmission over multipath fading channels. Inspired by recent works on deep learning based JSCC and model-based learning methods, we combine an autoencoder with orthogonal frequency division multiplexing (OFDM) to cope with multipath fading. The proposed encoder and decoder use convolutional neural networks (CNNs) and directly map the source images to complex-valued baseband samples for OFDM transmission. The multipath channel and OFDM are represented by non-trainable (deterministic) but differentiable layers so that the system can be trained end-to-end. Furthermore, our JSCC decoder further incorporates explicit channel estimation, equalization, and additional subnets to enhance the performance. The proposed method exhibits 2.5 – 4 dB SNR gain for the equivalent image quality compared to conventional schemes that employ state-of-the-art but separate source and channel coding such as Better Portable Graphics (BPG) and Low-Density Parity-Check (LDPC) schemes. The performance further improves when the system incorporates the channel state information (CSI) feedback. The proposed scheme is robust against OFDM signal clipping and parameter mismatch for the channel model used in training and evaluation.

A Delay-Efficient Deep Learning Approach for Lossless Turbo Source Coding

Lossless turbo source coding with decremental/incremental redundancy is a variable-length source coding scheme which employs turbo codes for data compression. Although the scheme offers low compression rates and lends itself to joint source-channel coding, it suffers from a large delay in the encoding phase. The delay is imposed by several tentative encoding-decoding procedures performed at the encoder to search for the minimum compression length. In this work, we apply machine learning to provide a highly accurate estimate of the proper compression length. The encoder starts its search from this estimated length, thus the delay of turbo source coding will decrease considerably. The preliminary results show a four-fold reduction in the encoding delay at the expense of a negligible increase in the compression rate.

Design and Analysis of Joint Source-Channel Code System with Fixed-Length Code

As the demands of multimedia and data services increase, efficient communication systems are being investigated to meet the high data rate requirements. Joint source-channel coding (JSCC) schemes were proposed for improving overall system performance. However, existing JSCC systems may suffer a symbol error rate (SER) performance loss when residual source redundancy is not fully exploited. This paper presents a novel, low-complexity JSCC system, which consists of a fixed-length source block code and an irregular convolutional channel code. A simple approach is proposed to design source codes that minimize the SER of source detection and guarantee the convergence of iterative source-channel decoding (ISCD). To improve the waterfall performance of ISCD, the channel code is optimized by using the extrinsic information transfer (EXIT) chart and the concept of irregular code. The channel code is constituted by recursive non-systematic convolutional (RNSC) subcodes. The weights of subcodes are optimized to make the EXIT curves of the channel decoder and the source decoder well-matched, and therefore, a near-capacity performance is achieved. Simulation results show that the proposed system achieves more than 1 dB gains and 0.3 dB gains compared to the separate source-channel code system and the other optimal JSCC systems, respectively. Additionally, the performance of the proposed system is within 1 dB deviation from the Shannon limit capacity.

A type-aware coding approach for unequal message protection

In this paper, to achieve an unequal message protection (UMP), we propose a type-aware coding approach. The proposed approach can be used to construct a UMP code with multiple classes of messages, and can also be employed as a finite-length joint source-channel coding (JSCC) where the source statistics is not required at the transmitter. At the transmitter, an information bit sequence is first encoded using a fixed-to-fixed-length type-aware description and then encoded by a given linear block code along with a “free-ride” approach. At the receiver, a type-search decoding algorithm is employed. Numerical results show that, 1) As a UMP coding, the type-aware coding can provide more protection for biased binary sequences; 2) As a finite-length JSCC, the type-aware coding can improve the average error performance for biased sources over the distribution-aware decoding.

Controversial Variable Node Selection-Based Adaptive Belief Propagation Decoding Algorithm Using Bit Flipping Check for JSCC Systems.

An end-to-end joint source–channel (JSC) encoding matrix and a JSC decoding scheme using the proposed bit flipping check (BFC) algorithm and controversial variable node selection-based adaptive belief propagation (CVNS-ABP) decoding algorithm are presented to improve the efficiency and reliability of the joint source–channel coding (JSCC) scheme based on double Reed–Solomon (RS) codes. The constructed coding matrix can realize source compression and channel coding of multiple sets of information data simultaneously, which significantly improves the coding efficiency. The proposed BFC algorithm uses channel soft information to select and flip the unreliable bits and then uses the redundancy of the source block to realize the error verification and error correction. The proposed CVNS-ABP algorithm reduces the influence of error bits on decoding by selecting error variable nodes (VNs) from controversial VNs and adding them to the sparsity of the parity-check matrix. In addition, the proposed JSC decoding scheme based on the BFC algorithm and CVNS-ABP algorithm can realize the connection of source and channel to improve the performance of JSC decoding. Simulation results show that the proposed BFC-based hard-decision decoding (BFC-HDD) algorithm ( = 1) and BFC-based low-complexity chase (BFC-LCC) algorithm ( = 1, = 3) can achieve about 0.23 dB and 0.46 dB of signal-to-noise ratio (SNR) defined gain over the prior-art decoding algorithm at a frame error rate (FER) = . Compared with the ABP algorithm, the proposed CVNS-ABP algorithm and BFC-CVNS-ABP algorithm achieve performance gains of 0.18 dB and 0.23 dB, respectively, at FER = .

Joint source-channel coding for 6G communications

In order to provide ultra low-latency and high energy-efficient communication for intelligences, the sixth generation (6G) wireless communication networks need to break out of the dilemma of the depleting gain of the separated optimization paradigm. In this context, this paper provides a comprehensive tutorial that overview how joint source-channel coding (JSCC) can be employed for improving overall system performance. For the purpose, we first introduce the communication requirements and performance metrics for 6G. Then, we provide an overview of the source-channel separation theorem and why it may not hold in practical applications. In addition, we focus on two new JSCC schemes called the double low-density parity-check (LDPC) codes and the double polar codes, respectively, giving their detailed coding and decoding processes and corresponding performance simulations. In a nutshell, this paper constitutes a tutorial on the JSCC scheme tailored to the needs of future 6G communications.