Semantic information processing for interoperability in the Industrial Internet of Things.

With the advent of the Internet of Everything (IoE), the concept of fully interconnected systems has become a reality, and the need for seamless communication and interoperability among different industrial systems has become more pressing than ever before. To address the challenges posed by massive data traffic, we demonstrate the potentials of semantic information processing in industrial manufacturing processes and then propose a brief framework of semantic processing and communication system for industrial network. In particular, the scheme is featured with task-orientation and collaborative processing. To illustrate its applicability, we provide examples of time series and images, as typical industrial data sources, for practical tasks, such as lifecycle estimation and surface defect detection. Simulation results show that semantic information processing achieves a more efficient way of information processing and exchanging, compared to conventional methods, which is crucial for handling the demands of future interconnected industrial networks.

Rate-Distortion-Perception Optimized Neural Speech Transmission System for High-Fidelity Semantic Communications.

We consider the problem of learned speech transmission. Existing methods have exploited joint source-channel coding (JSCC) to encode speech directly to transmitted symbols to improve the robustness over noisy channels. However, the fundamental limit of these methods is the failure of identification of content diversity across speech frames, leading to inefficient transmission. In this paper, we propose a novel neural speech transmission framework named NST. It can be optimized for superior rate-distortion-perception (RDP) performance toward the goal of high-fidelity semantic communication. Particularly, a learned entropy model assesses latent speech features to quantify the semantic content complexity, which facilitates the adaptive transmission rate allocation. NST enables a seamless integration of the source content with channel state information through variable-length joint source-channel coding, which maximizes the coding gain. Furthermore, we present a streaming variant of NST, which adopts causal coding based on sliding windows. Experimental results verify that NST outperforms existing speech transmission methods including separation-based and JSCC solutions in terms of RDP performance. Streaming NST achieves low-latency transmission with a slight quality degradation, which is tailored for real-time speech communication.