Deep Learning Enabled Semantic Communication Systems

TLDR

Deep‑learning–enabled end‑to‑end communication systems merge all physical‑layer blocks for joint transceiver optimization, while deep learning has also achieved great success in natural‑language processing. We aim to provide a new view on communication systems from the semantic level. DeepSC is a Transformer‑based semantic communication system for text transmission that maximizes capacity and minimizes semantic errors, employs transfer learning for adaptability across environments, and introduces a sentence‑similarity metric to evaluate performance. Compared with traditional systems ignoring semantics, DeepSC is more robust to channel variation and achieves better performance, especially at low SNR, as shown by extensive simulations.

Abstract

Recently, deep learned enabled end-to-end communication systems have been developed to merge all physical layer blocks in the traditional communication systems, which make joint transceiver optimization possible. Powered by deep learning, natural language processing has achieved great success in analyzing and understanding a large amount of language texts. Inspired by research results in both areas, we aim to provide a new view on communication systems from the semantic level. Particularly, we propose a deep learning based semantic communication system, named DeepSC, for text transmission. Based on the Transformer, the DeepSC aims at maximizing the system capacity and minimizing the semantic errors by recovering the meaning of sentences, rather than bit- or symbol-errors in traditional communications. Moreover, transfer learning is used to ensure the DeepSC applicable to different communication environments and to accelerate the model training process. To justify the performance of semantic communications accurately, we also initialize a new metric, named sentence similarity. Compared with the traditional communication system without considering semantic information exchange, the proposed DeepSC is more robust to channel variation and is able to achieve better performance, especially in the low signal-to-noise (SNR) regime, as demonstrated by the extensive simulation results.