Semantic Communications for Speech Signals
This work addresses the problem of robust speech communication in varying channel environments for communication systems, offering an incremental improvement over traditional bit-level systems.
The paper introduces DeepSC-S, a semantic communication system for speech signals that minimizes error at the semantic level. It recovers transmitted speech signals and demonstrates improved robustness to channel variations, outperforming traditional systems, especially in low SNR regimes.
We consider a semantic communication system for speech signals, named DeepSC-S. Motivated by the breakthroughs in deep learning (DL), 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 level or symbol level as in the traditional communication systems. Particularly, based on an attention mechanism employing squeeze-and-excitation (SE) networks, we design the transceiver as an end-to-end (E2E) system, which learns and extracts the essential speech information. Furthermore, in order to facilitate the proposed DeepSC-S to work well on dynamic practical communication scenarios, we find a model yielding good performance when coping with various channel environments without retraining process. The simulation results demonstrate that our proposed DeepSC-S is more robust to channel variations and outperforms the traditional communication systems, especially in the low signal-to-noise (SNR) regime.