Semantic Communication Systems for Speech Transmission

被引:243
|
作者
Weng, Zhenzi [1 ]
Qin, Zhijin [1 ]
机构
[1] Queen Mary Univ London, Sch Elect Engn & Comp Sci, London E1 4NS, England
关键词
Training; Adaptation models; Communication systems; Simulation; Multimedia systems; Semantics; Telephone sets; Deep learning; semantic communication; speech transmission; squeeze-and-excitation networks; DEEP; PERFORMANCE; INTERNET;
D O I
10.1109/JSAC.2021.3087240
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Semantic communications could improve the transmission efficiency significantly by exploring the semantic information. In this paper, we make an effort to recover the transmitted speech signals in the semantic communication systems, which minimizes the error at the semantic level rather than the bit or symbol level. Particularly, we design a deep learning (DL)-enabled semantic communication system for speech signals, named DeepSC-S. In order to improve the recovery accuracy of speech signals, especially for the essential information, DeepSC-S is developed based on an attention mechanism by utilizing a squeeze-and-excitation (SE) network. The motivation behind the attention mechanism is to identify the essential speech information by providing higher weights to them when training the neural network. Moreover, in order to facilitate the proposed DeepSC-S for dynamic channel environments, we find a general model to cope with various channel conditions without retraining. Furthermore, we investigate DeepSC-S in telephone systems as well as multimedia transmission systems to verify the model adaptation in practice. The simulation results demonstrate that our proposed DeepSC-S outperforms the traditional communications in both cases in terms of the speech signals metrics, such as signal-to-distortion ration and perceptual evaluation of speech distortion. Besides, DeepSC-S is more robust to channel variations, especially in the low signal-to-noise (SNR) regime.
引用
收藏
页码:2434 / 2444
页数:11
相关论文
共 50 条
  • [1] Semantic-Preserved Communication System for Highly Efficient Speech Transmission
    Han, Tianxiao
    Yang, Qianqian
    Shi, Zhiguo
    He, Shibo
    Zhang, Zhaoyang
    [J]. IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2023, 41 (01) : 245 - 259
  • [2] Deep Learning Enabled Semantic Communication Systems for Video Transmission
    Zhang, Zhenguo
    Yang, Qianqian
    He, Shibo
    Chen, Jiming
    [J]. 2023 IEEE 98TH VEHICULAR TECHNOLOGY CONFERENCE, VTC2023-FALL, 2023,
  • [3] SPEECH COMMUNICATION SYSTEMS
    KOCK, WE
    [J]. PROCEEDINGS OF THE INSTITUTE OF RADIO ENGINEERS, 1962, 50 (05): : 769 - +
  • [4] THE DEPENDENCE OF SPEECH RATE ON THE SEMANTIC LEVEL OF COMMUNICATION
    SULC, J
    [J]. ACTIVITAS NERVOSA SUPERIOR, 1982, 24 (03): : 171 - 172
  • [5] Enhanced semantic communication schemes for speech signals
    Yeo, Yerin
    Kim, Junghyun
    Song, Hong-Yeop
    [J]. ELECTRONICS LETTERS, 2024, 60 (08)
  • [6] Speech Semantic Communication Based on Swin Transformer
    Zhou, Ziliang
    Zheng, Shilian
    Chen, Jie
    Zhao, Zhijin
    Yang, Xiaoniu
    [J]. IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2024, 10 (03) : 756 - 768
  • [7] PSEUDO-ANALOG SPEECH TRANSMISSION IN MOBILE RADIO-COMMUNICATION SYSTEMS
    MIKI, T
    SUNDBERG, CEW
    SESHADRI, N
    [J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 1993, 42 (01) : 69 - 77
  • [8] STAR-RIS Assisted Information Transmission Based on Fairness in Semantic Communication Systems
    Xie, Ping
    Li, Fan
    Zhang, Mingchuan
    Quan, Wei
    Zhu, Junlong
    Cheng, Nan
    [J]. IEEE Transactions on Wireless Communications, 2024, 23 (11) : 17007 - 17020
  • [9] Communication framework for directed transmission of informative semantic
    Shi G.
    Yang M.
    Gao D.
    Chai J.
    [J]. Tongxin Xuebao/Journal on Communications, 2023, 44 (05): : 15 - 27
  • [10] Optimization of Image Transmission in Semantic Communication Networks
    Zhang, Wenjing
    Wang, Yining
    Chen, Mingzhe
    Luo, Tao
    Niyato, Dusit
    [J]. 2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 5965 - 5970