Design of a Speech Enhancement-Based Deep Semantic Autoencoder for Wireless Communications
Abstract
Speech communication plays a crucial role in the Internet of Things and autonomous networks. However, traditional communication systems suffer from insufficient semantic extraction and limited noise suppression capability. To address these issues, we propose a Speech enhancement-based Deep Semantic Autoencoder (S-DSA) communication system for wireless communications. It consists of a dual-branch semantic encoder, a channel encoder, a channel decoder, and two semantic decoders, enabling joint source-channel coding for robust transmission. A key novelty lies in an adaptive semantic noise decoupling mechanism that disentangles target speech semantics from noise representations through an interaction module, thus maintaining semantic consistency under low SNR conditions. Furthermore, a joint training strategy optimizes speech reconstruction and noise estimation, while a lightweight testing strategy reduces complexity by disabling the noise-decoding path. The proposed S-DSA enables more effective separation between speech and noise, and yields higher robustness as well as better reconstruction quality. These findings highlight the potential of the proposed S-DSA as a practical solution for next-generation intelligent wireless communications.
Versions
Related
- Antenna Coding by Pixel Antennas: Unlocking A New Dimension for Wireless Communications
- Sionna Bench: Towards Benchmarks in Wireless Communications
- Cold-Atom Rydberg Array with Spatiotemporal Multiplexing for High-Sensitivity Wireless Communications
- Secure Wireless Communications with Flexible Reflectors: Joint Position and Rotation Optimization for Physical Layer Security
- AI-Native Task-Oriented Semantic Communications over a Relay: Benefits and Vulnerabilities
BibTeX
@misc{han2026design,
title = {{Design of a Speech Enhancement-Based Deep Semantic Autoencoder for Wireless Communications}},
author = {Xiaoling Han and Bin Lin and Nan Wu and Tony Q. S. Quek},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.07361},
eprint = {2611.07361},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.07361},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Design of a Speech Enhancement-Based Deep Semantic Autoencoder for Wireless Communications
AU - Xiaoling Han
AU - Bin Lin
AU - Nan Wu
AU - Tony Q. S. Quek
PY - 2026
DA - 2026/11/05
PB - arXiv
DO - 10.48550/arxiv.2611.07361
UR - https://arxiv.org/abs/2611.07361
AB - Speech communication plays a crucial role in the Internet of Things and autonomous networks. However, traditional communication systems suffer from insufficient semantic extraction and limited noise suppression capability. To address these issues, we propose a Speech enhancement-based Deep Semantic Autoencoder (S-DSA) communication system for wireless communications. It consists of a dual-branch semantic encoder, a channel encoder, a channel decoder, and two semantic decoders, enabling joint source-channel coding for robust transmission. A key novelty lies in an adaptive semantic noise decoupling mechanism that disentangles target speech semantics from noise representations through an interaction module, thus maintaining semantic consistency under low SNR conditions. Furthermore, a joint training strategy optimizes speech reconstruction and noise estimation, while a lightweight testing strategy reduces complexity by disabling the noise-decoding path. The proposed S-DSA enables more effective separation between speech and noise, and yields higher robustness as well as better reconstruction quality. These findings highlight the potential of the proposed S-DSA as a practical solution for next-generation intelligent wireless communications.
ER -