Semantic communications execute intelligent tasks at the receiver by only transmitting necessary information. In this paper, we introduce TOS-ST, a task-oriented semantic communication system for speech transmission, which efficiently serves the semantic tasks at the receiver, including speech-to-text translation and speech-to-speech translation. Particularly, TOS-ST condenses the input speech in the source language and extracts the task-related semantics features prior to transmission. At the receiver, these features are recovered and utilized by the neural network-based semantic preserver and machine translation module to generate the uncorrupted text in the target language. To perform the speech-to-speech translation task, the translated text passes through a sophisticated neural network to obtain speech in the target language. According to the simulation results, the TOS-ST outperforms conventional speech transmission systems and exhibits higher robustness against channel impairment.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Task-Oriented Semantic Communications for Speech Transmission


    Contributors:
    Weng, Zhenzi (author) / Qin, Zhijin (author) / Tao, Xiaoming (author)


    Publication date :

    2023-10-10


    Size :

    1282515 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Task-Oriented Approaches to Automatic Speech Recognition

    Rosenberg, A. E. / Flanagan, J. L / Rabiner, L R. et al. | SAE | 1980


    Task Demand Oriented Lite Edge Communications for IoT

    Zhang, Junying / Du, Qinghe / Ren, Yijing et al. | IEEE | 2024


    Semantic Communication Approach for Multi-Task Image Transmission

    Zhang, Zhenguo / Yang, Qianqian / He, Shibo et al. | IEEE | 2022


    Task-oriented V2X Communications using Large Multi-modality Model

    Kim, Hyunsoo / Jeong, Seokhyun / Shim, Byonghyo | IEEE | 2024