What question did this study set out to answer?

This research aims to enhance semantic speech reconstruction using an innovative hybrid model.

May 24, 2026Open Access

DeepSC‐S‐MECA: A Hybrid Mamba‐ECA Framework for Robust Semantic Speech Communication

YYYerin YeoElectronics and Telecommunications Research Institute JKJunghyun KimSejong University

Key Points

This research aims to enhance semantic speech reconstruction using an innovative hybrid model.
Introduced DeepSC‐S‐MECA combining Mamba Transformer block and ECA‐ResNet block.
Evaluated performance under AWGN and Rician channels.
Compared against DeepSC‐S‐CBAMR and DeepSC‐S‐ECAR models.
DeepSC‐S‐MECA achieved higher SDR and PESQ metrics.
Reduced parameters and FLOPs by about 39% compared to DeepSC‐S‐CBAMR.
Demonstrated robust speech reconstruction capabilities.

Abstract

ABSTRACT This paper proposes DeepSC‐S‐MECA, a semantic communication model for improving speech semantic reconstruction. The model combines a Mamba Transformer (MambaTrans) block, which integrates a State Space Model (SSM) into a Transformer to capture temporal and contextual dependencies in sequential signals, and an ECA‐ResNet block, which applies efficient channel attention (ECA) to emphasize informative features. Experimental results under AWGN and Rician channels show that DeepSC‐S‐MECA achieves higher SDR and PESQ than DeepSC‐S‐CBAMR and DeepSC‐S‐ECAR, providing robust speech reconstruction while reducing parameters and FLOPs by about 39% compared with DeepSC‐S‐CBAMR.

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper