SS-L3: Generative Semantic Communication: How Generative Models Enhance Semantic Communications
Wed, 17 Apr, 08:20 - 10:20 (UTC +9)
Location: Room 205B
Session Type: Lecture
Session Co-Chairs: Eleonora Grassucci, Sapienza University of Rome and Jihong Park, Deakin University, Australia
Track: Special Sessions
Click the to view the manuscript on IEEE Xplore Open Preview
Wed, 17 Apr, 08:20 - 08:40 (UTC +9)
 

SS-L3.1: ENHANCING SEMANTIC COMMUNICATION WITH DEEP GENERATIVE MODELS: AN OVERVIEW
Eleonora Grassucci, Sapienza University of Rome, Italy; Yuki Mitsufuji, Sony Group Corporation, Japan; Ping Zhang, Beijing University of Posts and Telecommunications, China; Danilo Comminiello, Sapienza University of Rome, Italy
Wed, 17 Apr, 08:40 - 09:00 (UTC +9)
 

SS-L3.2: DIFFUSION-BASED SPEECH ENHANCEMENT WITH JOINT GENERATIVE AND PREDICTIVE DECODERS
Hao Shi, Kyoto University, Japan; Kazuki Shimada, Masato Hirano, Takashi Shibuya, Yuichiro Koyama, Zhi Zhong, Shusuke Takahashi, Sony Group Corporation, Japan; Tatsuya Kawahara, Kyoto University, Japan; Yuki Mitsufuji, Sony Group Corporation, Japan
Wed, 17 Apr, 09:00 - 09:20 (UTC +9)
 

SS-L3.3: DIFFSC: SEMANTIC COMMUNICATION FRAMEWORK WITH ENHANCED DENOISING THROUGH DIFFUSION PROBABILISTIC MODELS
Zeyu Jiang, Beijing University of Posts and Telecommunications, China; Xiaohong Liu, University College London, United Kingdom of Great Britain and Northern Ireland; Guoxing Yang, Weizhi Li, Beijing University of Posts and Telecommunications, China; Aini Li, Peng Cheng Laboratory, China; Guangyu Wang, Beijing University of Posts and Telecommunications, China
Wed, 17 Apr, 09:20 - 09:40 (UTC +9)
 

SS-L3.4: DIFFUSION MODELS FOR AUDIO SEMANTIC COMMUNICATION
Eleonora Grassucci, Christian Marinoni, Andrea Rodriguez, Danilo Comminiello, Sapienza University of Rome, Italy
Wed, 17 Apr, 09:40 - 10:00 (UTC +9)
 

SS-L3.5: SG2SC: A GENERATIVE SEMANTIC COMMUNICATION FRAMEWORK FOR SCENE UNDERSTANDING-ORIENTED IMAGE TRANSMISSION
Minxi Yang, Dahua Gao, Feng Xie, Jiaxuan Li, School of Artificial Intelligence, Xidian University, China; Xiaodan Song, Guangzhou Institute of Technology, Xidian University, China; Guangming Shi, School of Artificial Intelligence, Xidian University, China
Wed, 17 Apr, 10:00 - 10:20 (UTC +9)
 

SS-L3.6: SEMANTIC-PRESERVING IMAGE CODING BASED ON CONDITIONAL DIFFUSION MODELS
Francesco Pezone, Sapienza University of Rome, Italy; Osman Musa, Giuseppe Caire, Technische Universität Berlin, Germany; Sergio Barbarossa, Sapienza University of Rome, Italy