Deep Learning Enabled Semantic Communications with Speech Recognition and Synthesis

TL;DR

This paper introduces DeepSC-ST, a deep learning-based semantic communication system for speech that efficiently transmits and reconstructs speech signals, outperforming traditional methods especially in noisy environments.

Contribution

The paper presents a novel deep learning framework for semantic speech communication, integrating recognition and synthesis, with adaptive robustness to channel variations.

Findings

Significant data transmission reduction without performance loss

Outperforms conventional and existing DL communication systems in low SNR

Demonstrated effectiveness through simulation and software prototype

Abstract

In this paper, we develop a deep learning based semantic communication system for speech transmission, named DeepSC-ST. We take the speech recognition and speech synthesis as the transmission tasks of the communication system, respectively. First, 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, which significantly reduces the required amount of data transmission without performance degradation. Then, we perform speech synthesis at the receiver, which dedicates to re-generate the speech signals by feeding the recognized text and the speaker information into a neural network module. To enable the DeepSC-ST adaptive to dynamic channel environments, we identify a robust model to cope with different channel conditions. According to the simulation results, the proposed DeepSC-ST significantly outperforms conventional communication systems and existing DL-enabled communication systems, especially in the low signal-to-noise ratio (SNR) regime. A software demonstration is further developed as a proof-of-concept of the DeepSC-ST.