{"product_id":"deep-learning-enabled-semantic-communications-isbn-9781394306237","title":"Deep Learning Enabled Semantic Communications","description":"\u003cp\u003e\u003cb\u003eComprehensive overview of the principles, theories, and techniques behind deep learning-enabled semantic communications\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003e\u003ci\u003eDeep Learning Enabled Semantic Communications\u003c\/i\u003e explores the synergy between deep learning and semantic communication, particularly in the context of advancing 6G networks. It provides a focused introduction to the subject, systematically covering deep learning-enabled semantic communication systems and task-oriented semantic transmission paradigms in wireless communication. \u003c\/p\u003e\u003cp\u003eThe book reviews various aspects of semantic communications, including information theory, multimodal technologies, semantic noise, and semantic sensing. It explores cutting-edge semantic communication architectures, highlighting their advantages over traditional approaches and their potential to drive the future of intelligent information industry. The book also details applications of deep learning-based semantic communication systems across various sources, including text, speech, images, and videos, comprehensively addressing system design, performance optimization, and measurement metrics. \u003c\/p\u003e\u003cp\u003eThe book is divided into eight main parts, which cover foundational knowledge, system design, multimodal and multitask-oriented semantic communication systems, joint semantic sensing and sampling, semantic noise suppression, and generative AI enabled systems. \u003c\/p\u003e\u003cp\u003eWritten by a diverse group of experts in academia and research institutions, \u003ci\u003eDeep Learning Enabled Semantic Communications\u003c\/i\u003e includes information on: \u003c\/p\u003e\u003cul\u003e \u003cli\u003eFundamental knowledge about the deep learning and semantic communications, including the history, neural networks, and semantic information theory\u003c\/li\u003e \u003cli\u003eCompression of multimodal inputs, extraction of global semantic information, and the design of neural networks to boost the capability of handling lengthy speech\u003c\/li\u003e \u003cli\u003eIncorporation of different sources to extract semantic features and serve diverse intelligent tasks at the receiver\u003c\/li\u003e \u003cli\u003eIntroduction of semantic impairments in communications to uncover how to design  robust systems\u003c\/li\u003e \u003cli\u003eJoint design of data sampling, compression, and coding schemes under the guidance of semantic information\u003c\/li\u003e \u003cli\u003eFramework of generative semantic communications to detail the principles of incorporating generative models into semantic communications\u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003e\u003ci\u003eDeep Learning Enabled Semantic Communications\u003c\/i\u003e is an essential learning resource and reference for graduate and undergraduate students pursuing degrees in wireless communications, signal processing, or deep learning as well as engineers in the telecommunications and IT industries focusing on wireless communication techniques. \u003c\/p\u003e\u003cp\u003eForeword ix\u003c\/p\u003e \u003cp\u003ePreface xi\u003c\/p\u003e \u003cp\u003eAcknowledgments xv\u003c\/p\u003e \u003cp\u003eAcronyms xvii\u003c\/p\u003e \u003cp\u003eNotations xxi\u003cbr\u003e\u003cbr\u003e\u003c\/p\u003e \u003cp\u003e1 Introduction 1\u003c\/p\u003e \u003cp\u003e1.1 Conventional Communications vs. Semantic Communications  2\u003c\/p\u003e \u003cp\u003e1.1.1 Three-Level Communications . . . . . . . . . . . . . 2\u003c\/p\u003e \u003cp\u003e1.1.2 History of Semantic Communications . . . . . . . . . 5\u003c\/p\u003e \u003cp\u003e1.2 Introducing Deep Learning to Semantic Communications . . . . 6\u003c\/p\u003e \u003cp\u003e1.2.1 Deep Learning Basics . . . . . . . . . . . . . . . . . . 6\u003c\/p\u003e \u003cp\u003e1.2.2 Deep Learning Enabled Semantic Communications . 17\u003c\/p\u003e \u003cp\u003e1.3 Semantic Communications for Further Networks . . . . . . . . . 20\u003cbr\u003e\u003cbr\u003e\u003c\/p\u003e \u003cp\u003e2 Semantic Information Theory 31\u003c\/p\u003e \u003cp\u003e2.1 Semantic Entropy . . . . . . . . . . . . . . . . . . . . . . . . . . . 31\u003c\/p\u003e \u003cp\u003e2.1.1 Logical Probability-based . . . . . . . . . . . . . . . . 32\u003c\/p\u003e \u003cp\u003e2.1.2 Synonymous mapping-based . . . . . . . . . . . . . . 34\u003c\/p\u003e \u003cp\u003e2.1.3 Fuzzy Theory-based . . . . . . . . . . . . . . . . . . . 37\u003c\/p\u003e \u003cp\u003e2.1.4 Task-based . . . . . . . . . . . . . . . . . . . . . . . . 38\u003c\/p\u003e \u003cp\u003e2.2 Semantic Channel Capacity . . . . . . . . . . . . . . . . . . . . . 38\u003c\/p\u003e \u003cp\u003e2.2.1 Logical Probability-based . . . . . . . . . . . . . . . . 39\u003c\/p\u003e \u003cp\u003e2.2.2 Sympuous Mapping based . . . . . . . . . . . . . . . 40\u003c\/p\u003e \u003cp\u003e2.3 Semantic Source Coding Theorem . . . . . . . . . . . . . . . . . 41\u003c\/p\u003e \u003cp\u003e2.3.1 Logical Probability-based . . . . . . . . . . . . . . . . 42\u003c\/p\u003e \u003cp\u003e2.3.2 Sympuous Mapping-based . . . . . . . . . . . . . . . 43\u003c\/p\u003e \u003cp\u003e2.4 Semantic Channel Coding Theorem . . . . . . . . . . . . . . . . 44\u003c\/p\u003e \u003cp\u003e2.4.1 Logical Probability-based . . . . . . . . . . . . . . . 44\u003c\/p\u003e \u003cp\u003e2.4.2 Synonymous Mapping-based . . . . . . . . . . . . . 44\u003c\/p\u003e \u003cp\u003e2.5 Information Bottleneck . . . . . . . . . . . . . . . . . . . . . . . . 45\u003c\/p\u003e \u003cp\u003e2.5.1 Classical Information Bottleneck . . . . . . . . . . . . 45\u003c\/p\u003e \u003cp\u003e2.5.2 Knowledge Collision based Information Bottleneck . 47\u003cbr\u003e\u003cbr\u003e\u003c\/p\u003e \u003cp\u003e3 Joint Semantic-Channel Coding for Source Reconstruction 51\u003c\/p\u003e \u003cp\u003e3.1 Semantic Communications for Text . . . . . . . . . . . . . . . . 52\u003c\/p\u003e \u003cp\u003e3.1.1 Joint Semantic-Channel Coding for Text . . . . . . . 54\u003c\/p\u003e \u003cp\u003e3.2 Semantic Communications for Speech . . . . . . . . . . . . . . . 58\u003c\/p\u003e \u003cp\u003e3.2.1 Joint Semantic-Channel Coding for Speech . . . . . 60\u003c\/p\u003e \u003cp\u003e3.3 Semantic Communications for Image . . . . . . . . . . . . . . . . 64\u003c\/p\u003e \u003cp\u003e3.3.1 Joint Semantic-Channel Coding for Image . . . . . . 66\u003c\/p\u003e \u003cp\u003e3.4 Performance Metrics . . . . . . . . . . . . . . . . . . . . . . . . . 71\u003c\/p\u003e \u003cp\u003e3.4.1 Performance Metrics for Text Accuracy . . . . . . . 71\u003c\/p\u003e \u003cp\u003e3.4.2 Performance Metrics for Speech Quality . . . . . . . 74\u003c\/p\u003e \u003cp\u003e3.4.3 Performance Metrics for Image Quality . . . . . . . . 74\u003cbr\u003e\u003cbr\u003e\u003c\/p\u003e \u003cp\u003e4 Task-Oriented Semantic Communications 85\u003c\/p\u003e \u003cp\u003e4.1 Single-Modal Task-Oriented Semantic Communications . . . . . 86\u003c\/p\u003e \u003cp\u003e4.1.1 Semantic Communications for Machine Translation 86\u003c\/p\u003e \u003cp\u003e4.1.2 Semantic Communications for Speech Recognition and Synthesis . . . . . . . . . . . . . . . . . . . . . . . 91\u003c\/p\u003e \u003cp\u003e4.2 Multimodal Task-Oriented Semantic Communications . . . . . . 104\u003c\/p\u003e \u003cp\u003e4.2.1 Semantic Communication Systems for Visual Question Answering . . . . . . . . . . . . . . . . . . . . . . 104\u003cbr\u003e\u003cbr\u003e\u003c\/p\u003e \u003cp\u003e5 Joint Sensing and Semantic Communications 115\u003c\/p\u003e \u003cp\u003e5.1 Introduction and Framework of Joint Sampling and Coding . . 116\u003c\/p\u003e \u003cp\u003e5.2 Joint Semantic Sampling and Coding for Image . . . . . . . . . 119\u003c\/p\u003e \u003cp\u003e5.2.1 Semantic-aware Image Compressed Sensing . . . . . 120\u003c\/p\u003e \u003cp\u003e5.2.2 Adaptive Sampling and Semantic-Channel Coding . 127\u003c\/p\u003e \u003cp\u003e5.3 Joint Semantic Sampling and Coding for Video . . . . . . . . . 135\u003c\/p\u003e \u003cp\u003e5.3.1 Semantic-based Video Sampling and Reconstruction 137\u003cbr\u003e\u003cbr\u003e\u003c\/p\u003e \u003cp\u003e6 Semantic Impairments in Communications 145\u003c\/p\u003e \u003cp\u003e6.1 JSCC Framework with Semantic Impairments . . . . . . . . . . 146\u003c\/p\u003e \u003cp\u003e6.2 Source Semantic Impairments Suppression . . . . . . . . . . . . 149\u003c\/p\u003e \u003cp\u003e6.2.1 Robust Semantic Communications for Text . . . . . 149\u003c\/p\u003e \u003cp\u003e6.2.2 Robust Semantic Communications for Speech . . . . 157\u003c\/p\u003e \u003cp\u003e6.2.3 Robust Semantic Communications for Image . . . . 165\u003c\/p\u003e \u003cp\u003e6.3 Knowledge Base Semantic Impairments Suppression . . . . . . . 177\u003c\/p\u003e \u003cp\u003e6.3.1 Robust Semantic Knowledge Base . . . . . . . . . . 178\u003c\/p\u003e \u003cp\u003e \u003c\/p\u003e \u003cp\u003e7 Generative AI Enabled Semantic Communications 191\u003c\/p\u003e \u003cp\u003e7.1 Introducing Generative Models to Semantic Communications . 191\u003c\/p\u003e \u003cp\u003e7.2 Framework of Generative Semantic Communications . . . . . . 195\u003c\/p\u003e \u003cp\u003e7.2.1 Main Components of Generative Semantic Communication System . . . . . . . . . . . . . . . . . . . . . 197\u003c\/p\u003e \u003cp\u003e7.2.2 Key Interactions and Processes . . . . . . . . . . . . 201\u003c\/p\u003e \u003cp\u003e7.3 Demonstration of Generative Semantic Communication for Video Conferencing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 203\u003c\/p\u003e \u003cp\u003e7.4 Applications of Semantic Communications in Other Scenarios . 206\u003c\/p\u003e \u003cp\u003e7.4.1 Immersive Communications . . . . . . . . . . . . . . 206\u003c\/p\u003e \u003cp\u003e7.4.2 Autonomous Driving . . . . . . . . . . . . . . . . . . 208\u003c\/p\u003e \u003cp\u003e7.4.3 Smart Cities . . . . . . . . . . . . . . . . . . . . . . . 209\u003c\/p\u003e \u003cp\u003e7.4.4 Satellite Networks . . . . . . . . . . . . . . . . . . . . 210\u003cbr\u003e\u003cbr\u003e\u003c\/p\u003e \u003cp\u003e8 Conclusions and Challenges 217\u003c\/p\u003e  \u003cp\u003e\u003cb\u003eZhijin Qin\u003c\/b\u003e is an Associate Professor with Tsinghua University, China. She is an Associate Editor for IEEE Transactions on Communications, IEEE Transactions on Cognitive Networking, and IEEE Communications Letters. \u003c\/p\u003e\u003cp\u003e\u003cb\u003eDr. Huiqiang Xie,\u003c\/b\u003e  is an Associate Professor at Jinan University, Guangzhou, Guangdong, China. \u003c\/p\u003e\u003cp\u003e\u003cb\u003eZhenzi Weng\u003c\/b\u003e is a Postdoctoral researcher at Imperial College London, UK. \u003c\/p\u003e\u003cp\u003e\u003cb\u003eXiaoming Tao\u003c\/b\u003e is a Professor with the Department of Electronic Engineering at Tsinghua University. She is also a Senior Member of the IEEE.\u003c\/p\u003e","brand":"Wiley-IEEE Press","offers":[{"title":"Default Title","offer_id":47989033009381,"sku":"NP9781394306237","price":140.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9781394306237.jpg?v=1761782523","url":"https:\/\/k12savings.com\/es\/products\/deep-learning-enabled-semantic-communications-isbn-9781394306237","provider":"K12savings","version":"1.0","type":"link"}