Low-latency configurable speech transmission presents significant challenges in modern communication systems. Traditional methods rely on separate source and channel coding, which often degrades performance under low-...
详细信息
Low-latency configurable speech transmission presents significant challenges in modern communication systems. Traditional methods rely on separate source and channel coding, which often degrades performance under low-latency constraints. Moreover, non-configurable systems require separate training for each condition, limiting their adaptability in resource-constrained scenarios. This paper proposes a configurable low-latency deep Joint Source-channel coding (JSCC) system for speech transmission. The system can be configured for varying signal-to-noise ratios (SNR), wireless channel conditions, or bandwidths. A joint source-channel encoder based on deep neural networks (DNN) is used to compress and transmit analog-coded information, while a configurable decoder reconstructs speech from noisy compressed signals. The system latency is adaptable based on the input speech length, achieving a minimum latency of 2 ms, with a lightweight architecture of 25 k parameters, significantly fewer than state-of-the-art systems. The simulation results demonstrate that the proposed system outperforms conventional separate source-channel coding systems in terms of speech quality and intelligibility, particularly in low-latency and noisy channel conditions. It also shows robustness in fixed configured scenarios, though higher latency conditions and better channel environments favor traditional coding systems.
With the recent advancements in edge artificial intelligence (AI), future sixth-generation (6G) networks need to support new AI tasks such as classification and clustering apart from data recovery. Motivated by the su...
详细信息
With the recent advancements in edge artificial intelligence (AI), future sixth-generation (6G) networks need to support new AI tasks such as classification and clustering apart from data recovery. Motivated by the success of deep learning, the semantic-aware and task-oriented communications with deep joint source and channel coding (JSCC) have emerged as new paradigm shifts in 6G from the conventional data-oriented communications with separate source and channel coding (SSCC). However, most existing works focused on the deep JSCC designs for one task of data recovery or AI task execution independently, which cannot be transferred to other unintended tasks. Differently, this paper investigates the JSCC semantic communications to support multi-task services, by performing the image data recovery and classification task execution simultaneously. First, we propose a new end-to-end deep JSCC framework by unifying the coding rate reduction maximization and the mean square error (MSE) minimization in the loss function. Here, the coding rate reduction maximization facilitates the learning of discriminative features for enabling to perform classification tasks directly in the feature space, and the MSE minimization helps the learning of informative features for high-quality image data recovery. Next, to further improve the robustness against variational wireless channels, we propose a new gated deep JSCC design, in which a gated net is incorporated for adaptively pruning the output features to adjust their dimensions based on channel conditions. Finally, we present extensive numerical experiments to validate the performance of our proposed deep JSCC designs as compared to various benchmark schemes. It is shown that our proposed designs simultaneously provide efficient multi-task services, and the proposed gated deep JSCC framework efficiently reduces the communication overhead with only marginal performance loss. It is also shown that performing the classification task on t
Information theory has driven the information and communication technology industry for over 70 years. Great successes have been achieved in both academia and industry. In theory, polar codes and spatially coupled low...
详细信息
In recent years, deep learning-based joint source-channel coding (DJSCC) has gained significant attention for its impressive performance in image transmission. Unlike traditional separate source-channel coding (SSCC) ...
详细信息
In recent years, deep learning-based joint source-channel coding (DJSCC) has gained significant attention for its impressive performance in image transmission. Unlike traditional separate source-channel coding (SSCC) methods, DJSCC performs particularly well in low signal-to-noise ratio (SNR) and limited bandwidth environments. However, ensuring the security of private information during transmission remains a critical concern. A notable limitation of DJSCC is its incompatibility with traditional encryption methods used for secure communications, making it vulnerable to eavesdropping attacks. To address this issue, we propose integrating a chaotic map encryption method into the DJSCC framework for secure wireless image transmission. This approach leverages chaotic sequence to shuffle the position of the elements in latent space without altering the values of the latent tensor. This allows the encryption process to be designed independently of DJSCC, eliminating the need for re-training the end-to-end model. Our proposed method preserves DJSCC's superior transmission characteristics, ensuring high-quality image reconstruction at the receiver, while effectively ensuring the security against deep learning-based known plaintext attacks (Deep KPA).
This paper provides a comprehensive survey of recent advances in deep learning (DL) techniques for channel coding problems. Inspired by the recent successes of DL in a variety of research domains, its applications to ...
详细信息
This paper provides a comprehensive survey of recent advances in deep learning (DL) techniques for channel coding problems. Inspired by the recent successes of DL in a variety of research domains, its applications to physical layer technologies have been extensively studied in recent years, and they are expected to be a potential breakthrough in supporting the emerging use cases of the next generation wireless communication systems such as 6G. In this paper, we focus exclusively on channel coding problems and review existing approaches that incorporate advanced DL techniques into code design and channel decoding. After briefly introducing the background of recent DL techniques, we categorize and summarize a variety of approaches, including model-free and model-based DL, for the design and decoding of modern error-correcting codes, such as low-density parity check (LDPC) codes and polar codes, to highlight their potential advantages and challenges. Finally, the paper concludes with a discussion of open issues and future research directions in channel coding.
In the source coding problem with cost constraint, a cost function is defined over the code alphabet. This can be regarded as a noiseless channel coding problem with cost constraint. In this case, we will not distingu...
详细信息
In the source coding problem with cost constraint, a cost function is defined over the code alphabet. This can be regarded as a noiseless channel coding problem with cost constraint. In this case, we will not distinguish between the input alphabet and the output alphabet of the channel. However, we must distinguish them for a noisy channel. In the channel coding problem with cost constraint so far, the cost function is defined over the input alphabet of the noisy channel. In this paper, we define the cost function over the output alphabet of the channel. And, the cost is paid only after the received word is observed. Note that the cost is a random variable even if the codeword is fixed. We show the channel capacity with cost constraint defined over the output alphabet. Moreover, we generalize it to tolerate some decoding error and some cost overrun. Finally, we show that the cost constraint can be described on a subset of arbitrary set which may have no structure.
Joint source-channel coding (JSCC) has achieved great success due to the introduction of deep learning (DL). Compared to traditional separate source-channel coding (SSCC) schemes, the advantages of DL-based JSCC (DJSC...
详细信息
Joint source-channel coding (JSCC) has achieved great success due to the introduction of deep learning (DL). Compared to traditional separate source-channel coding (SSCC) schemes, the advantages of DL-based JSCC (DJSCC) include high spectrum efficiency, high reconstruction quality, and relief of "cliff effect". However, it is difficult to couple existing secure communication mechanisms (e.g., encryption-decryption mechanism) with DJSCC in contrast with traditional SSCC schemes, which hinders the practical usage of this emerging technology. To this end, our paper proposes a novel method called DL-based joint protection and source-channel coding (DJPSCC) for images that can successfully protect the visual content of the plain image without significantly sacrificing image reconstruction performance. The idea of the design is to use a neural network to conduct visual protection, which converts the plain image to a visually protected one with the consideration of its interaction with DJSCC. During the training stage, the proposed DJPSCC method learns: 1) deep neural networks for image protection and image deprotection, and 2) an effective DJSCC network for image transmission in the protected domain. Compared to existing source protection methods applied with DJSCC transmission, the DJPSCC method achieves much better reconstruction performance.
In our relentless pursuit of improving healthcare and elevating wellness standards, we have unveiled a groundbreaking approach that amalgamates the cutting-edge realms of quantum optics, channel coding, artificial int...
详细信息
In our relentless pursuit of improving healthcare and elevating wellness standards, we have unveiled a groundbreaking approach that amalgamates the cutting-edge realms of quantum optics, channel coding, artificial intelligence (AI), and Advanced Optical Systems (optical IoT). This innovative collaboration is meticulously designed to fortify healthcare systems while enhancing cybersecurity protocols in the healthcare imaging sector. At the heart of this transformative initiative lies the cyber security threat and detecting analysis (CYSTDA), a groundbreaking framework that seamlessly integrates the strengths of AI, quantum optics, and advanced optical IoT to secure sensitive imaging data and systems. Quantum optics, known for its precision and sensitivity, offers a robust foundation for safeguarding imaging data. By leveraging quantum principles, it becomes possible to encode and protect visual information in an exceptionally secure manner. channel coding techniques, initially designed for communication systems, are adapted to ensure the integrity and confidentiality of imaging data transmission, mitigating the risks of cyberattacks. On the other hand, AI plays a crucial role in CYSTDA by providing advanced threat detection techniques using deep learning models such as neural networks, enabling real-time monitoring and analysis of imaging data, and detecting anomalies and potential security breaches. This approach enhances the cybersecurity posture of imaging systems and safeguards the confidentiality of the visual information. Integration of advanced optical IoT is the other advantage of CYSTDA for improving cybersecurity in imaging;by deploying interconnected security devices and sensors, CYSTDA establishes a dynamic and secured ecosystem. Overall, the CYSTDA, which leverages the advanced technologies discussed earlier, was used to elevate cybersecurity protocols for imaging. This framework has the potential to significantly enhance the security of visual data, ima
Semantic communication has emerged as a promising solution to meet the growing demand for efficient data transmission in the information age. Unlike traditional communication methods that focus on transmitting raw dat...
详细信息
Joint Source-channel coding (JSCC) is a powerful technique that allows for the efficient transmission of information by simultaneously considering the characteristics of both the source and the channel. The recently p...
详细信息
Joint Source-channel coding (JSCC) is a powerful technique that allows for the efficient transmission of information by simultaneously considering the characteristics of both the source and the channel. The recently proposed Exponential Golomb Error Correction (ExpGEC) and Rice Error Correction (REC) codes provide generalized JSCC schemes for the near capacity coding of symbols drawn from large or infinite alphabets. Yet these require impractical decoding structures, with large buffers and inflexible system design, this was mitigated by the introduction of the Reordered Elias Gamma Error Correction (REGEC) which itself had limited flexibility with regards to source distribution. In this paper, we propose a novel Reordered Exponential Golomb Error Correction (RExpGEC) coding scheme, which is a JSCC technique designed for flexible and practical near-capacity performance. The proposed RExpGEC encoder and decoder are presented and its performance is analysed using Extrinsic Information Transfer (EXIT) charts. The flexibility of the RExpGEC is shown via the novel trellis encoder and decoder design. Finally, the Symbol Error Rate (SER) performance of RExpGEC code is compared when integrated into the novel RExpGEC-URC-QPSK scheme against other comparable JSCC and Separate Source channel coding (SSCC) benchmarkers. Specifically the RExpGEC-URC-QPSK scheme is compared against the REGEC-URC-QPSK scheme, and a serial concatenation of the Exponential Golomb and Convolution Code, which becomes the novel Exp-CC-URC-QPSK scheme. Our simulation results demonstrate the performance gains and flexibility of the proposed RExpGEC-URC-QPSK scheme against the benchmarkers in providing reliable and efficient communications. Specifically, the RExpGEC-URC-QPSK scheme outperforms the SSCC in a uncorrelated Rayleigh fading channel by 2 to 3.6 dB (dependent on source distribution). Furthermore, the RExpGEC-URC-QPSK scheme consistently operates within 2.5 dB of channel capacity when measuring Eb
暂无评论