TransCoder: A Transformer-Based Neural-Enhancement Framework for Channel Codes

Abstract

Communication over noisy channels relies on error-correcting codes (ECCs) tailored to system constraints. Neural decoders can improve ECC reliability, yet their high computational complexity hinders practical deployment. We instead design a transformer-based transmission scheme that improves the reliability of existing ECCs without replacing them. We call this approach TransCoder, alluding both to its function and architecture. TransCoder operates as a code-adaptive module deployable at the transmitter, the receiver, or both. A block-attention neural decoder iteratively refines the channel observations together with the soft outputs of a conventional decoder. Across LDPC, BCH, Polar, and Turbo codes and a wide SNR range, TransCoder significantly lowers the block error rate (BLER) at complexity comparable to conventional decoders. Gains are largest at moderate blocklengths (64–512) and lower rates, regimes in which existing neural decoders struggle despite their much higher complexity. For 5G NR LDPC codes with blocklengths $\geq 400$ , the decoder-only variant still achieves significant performance improvements, especially at high SNR. These results position TransCoder as a practical solution for resource-constrained wireless devices.