AI 中文总结
本文提出语义辅助迭代解码（Sem-IR）方案，结合ByT5语言模型与物理层迭代，在8dB时较无语义反馈的NOMA将块错误率降低一个数量级，性能优于TDMA。
AI 中文摘要
本文针对共享自然语言源的上行非正交传输，提出了语义辅助迭代解码（Sem-IR）方案。K个用户各持有同一句子的一个片段，在加性高斯白噪声（AWGN）信道上进行低密度奇偶校验（LDPC）编码的叠加传输。在基站侧，迭代基本信号估计器（ESE）与K个并行LDPC解码器逐步消除用户间干扰。由于高功率用户更早通过奇偶校验和语言合理性检查，其解码字节构成剩余用户的可靠语言前缀；微调后的ByT5字节级语言模型利用该前缀，为未收敛用户预测字节后验概率。字节后验概率被边缘化至比特级对数似然比，并在迭代环路内与LDPC后验概率进行凸组合，所得反馈闭合了语言模型与物理层迭代间的环路。仿真结果表明，Sem-IR在块错误率（BLER）上优于正交时分多址（TDMA）和无语义反馈的同类NOMA接收机，在8dB时较NOMA实现了一个数量级的降低。
英文摘要
This paper proposes semantic-aided iterative decoding (Sem-IR) for uplink non-orthogonal transmission of a shared natural-language source. K users each hold one segment of a common sentence and superimpose low-density parity-check (LDPC) coded transmissions over an additive white Gaussian noise (AWGN) channel. At the base station, an iterative elementary signal estimator (ESE) and K parallel LDPC decoders progressively cancel inter-user interference. As high-power users pass both parity and language-plausibility checks earlier, their decoded bytes form a reliable linguistic prefix for the remaining users; a fine-tuned ByT5 byte-level language model exploits this prefix to predict byte posteriors for the unconverged user. The byte posteriors are marginalized to bit-level log-likelihood ratios and convex-combined with the LDPC posteriors inside the iterative loop. The resulting feedback closes the loop between the language model and the physical-layer iteration. Simulations show that Sem-IR outperforms orthogonal time-division access (TDMA) and the same NOMA receiver without semantic feedback in block error rate (BLER), yielding an order-of-magnitude reduction over NOMA at 8 dB.
Comments6 pages, 7 figures, 1 table
