Z
Zhenzi Weng
Researcher at Queen Mary University of London
Publications - 6
Citations - 259
Zhenzi Weng is an academic researcher from Queen Mary University of London. The author has contributed to research in topics: Communications system & Communication channel. The author has an hindex of 3, co-authored 5 publications receiving 17 citations.
Papers
More filters
Journal ArticleDOI
Semantic Communication Systems for Speech Transmission
Zhenzi Weng,Zhijin Qin +1 more
TL;DR: This paper designs a deep learning (DL)-enabled semantic communication system for speech signals, named DeepSC-S, developed based on an attention mechanism by utilizing a squeeze-and-excitation (SE) network, which outperforms the traditional communications in both cases in terms of the speech signals metrics.
Posted Content
Semantic Communications for Speech Signals
TL;DR: The simulation results demonstrate that the proposed DeepSC-S is more robust to channel variations and outperforms the traditional communication systems, especially in the low signal-to-noise (SNR) regime.
Proceedings ArticleDOI
Semantic Communications for Speech Signals
TL;DR: In this article, a semantic communication system for speech signals, named DeepSC-S, is proposed, which minimizes the error at the semantic level rather than the bit level or symbol level as in the traditional communication systems.
Journal ArticleDOI
Deep Learning Enabled Semantic Communications with Speech Recognition and Synthesis
TL;DR: In this article , a deep learning based semantic communication system for speech transmission, named DeepSC-ST, is proposed, where the speech recognition-related semantic features are extracted for transmission by a joint semantic-channel encoder and the text is recovered at the receiver based on the received semantic features.
Posted Content
Semantic Communication Systems for Speech Transmission
Zhenzi Weng,Zhijin Qin +1 more
TL;DR: In this paper, a deep learning-enabled semantic communication system for speech signals, named DeepSC-S, is developed based on an attention mechanism by utilizing a squeeze-and-excitation (SE) network.