arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.02478cs.LGcs.AIeess.SP
收藏

利用深度生成模型增强语义通信——ICASSP特别会议综述

Enhancing Semantic Communication with Deep Generative Models -- An ICASSP Special Session Overview

Sapienza University of Rome(罗马第一大学);Sony Group Corporation(索尼集团公司);Beijing University of Posts and Telecommunications(北京邮电大学)

Eleonora Grassucci, Yuki Mitsufuji, Ping Zhang, Danilo Comminiello

AI总结:

本文从机器学习视角综述了语义通信的挑战,指出深度生成模型能有效解决复杂语义信息提取、数据重建及信道鲁棒性问题,并为下一代生成式语义通信框架规划了新研究路径。

摘要:

语义通信有望在塑造未来AI驱动的通信系统格局中发挥关键作用。从原始复杂内容中提取语义信息并在接收端重新生成语义一致的数据(可能对信道损坏具有鲁棒性)的挑战,可以通过深度生成模型来解决。这篇ICASSP特别会议综述论文从机器学习视角揭示了语义通信的挑战,并展示了深度生成模型将如何显著增强语义通信框架在处理现实世界复杂数据、提取和利用语义信息以及对信道损坏保持鲁棒性方面的能力。在确立这一新兴领域的同时,本文为下一代生成式语义通信框架规划了新的研究路径。

英文摘要:

Semantic communication is poised to play a pivotal role in shaping the landscape of future AI-driven communication systems. Its challenge of extracting semantic information from the original complex content and regenerating semantically consistent data at the receiver, possibly being robust to channel corruptions, can be addressed with deep generative models. This ICASSP special session overview paper discloses the semantic communication challenges from the machine learning perspective and unveils how deep generative models will significantly enhance semantic communication frameworks in dealing with real-world complex data, extracting and exploiting semantic information, and being robust to channel corruptions. Alongside establishing this emerging field, this paper charts novel research pathways for the next generative semantic communication frameworks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑