# Deep Learning for Joint Narrowband Interference Cancellation and Soft Demodulation in OFDM Systems

arXiv: https://arxiv.org/abs/2607.08717 · HTML: https://mlsanity.com/paper/2607.08717/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 35 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 11 of 11)

- [An Introduction to Deep Learning for the Physical Layer](https://mlsanity.com/paper/1702.00832/) (2017)
- [Model-Driven Deep Learning for Physical Layer Communications](https://mlsanity.com/paper/1809.06059/) (2018)
- [Interference Suppression Using Deep Learning: Current Approaches and Open Challenges](https://mlsanity.com/paper/2112.08988/) (2021)
- ["Machine LLRning": Learning to Softly Demodulate](https://mlsanity.com/paper/1907.01512/) (2019)
- [Complex Signal Denoising and Interference Mitigation for Automotive Radar Using Convolutional Neural Networks](https://mlsanity.com/paper/1906.10044/) (2019)
- [Interference Management for Integrated Sensing and Communication Systems: A Survey](https://mlsanity.com/paper/2403.16189/) (2024)
- [Upper Mid-Band Spectrum for 6G: Vision, Opportunity and Challenges](https://mlsanity.com/paper/2502.17914/) (2025)
- [Narrowband Interference Detection via Deep Learning](https://mlsanity.com/paper/2301.09607/) (2023)
- [6G Wireless Communications in 7-24 GHz Band: Opportunities, Techniques, and Challenges](https://mlsanity.com/paper/2310.06425/) (2023)
- [Eliminating NB-IoT Interference to LTE System: a Sparse Machine Learning Based Approach](https://mlsanity.com/paper/2005.03092/) (2020)
- [Spectrum Sharing Across Terrestrial and Non-Terrestrial Services in the FR3 Upper Midband](https://mlsanity.com/paper/2606.13511/) (2026)

## Abstract (arXiv)

Narrowband interference (NBI) severely degrades orthogonal frequency-division multiplexing (OFDM) systems by corrupting subcarriers and rendering classical soft demodulation ineffective. Conventional compressed-sensing (CS) mitigation exhibits high sequential latency and leaves structured, non-Gaussian residuals that cause log-likelihood ratio (LLR) unreliability, decoder saturation, and severe error floors when employing classical Gaussian demappers. We resolve this pipeline mismatch using a unified deep learning framework for joint NBI cancellation and robust soft demodulation. First, NBI-CNet employs a physics-informed convolutional architecture to estimate NBI parameters and remove multi-tone interference in a single forward pass. Without requiring prior knowledge of the active interferer count, NBI-CNet reduces computational complexity by up to 60% (N=2048, Q=64) compared to the state-of-the-art EOMP-IDS algorithm. Second, LLR-CNet acts as a structural whitener by mapping non-Gaussian post-mitigation residuals onto well-calibrated soft metrics. Simulations demonstrate that this joint framework eliminates the error floors inherent to traditional baselines across dense grids. Under severe interference (SIR=-10 dB), the pipeline operates within a 0.2 to 0.5 dB SNR margin of the optimal iterative baseline at a target block error rate (BLER) of 10-4. Under mild interference (SIR=10 dB) with heavy spectral overlap (Q=12), where classical greedy algorithms erroneously subtract valid data components and corrupt the payload, NBI-CNet avoids signal-peak confusion to deliver a coding gain exceeding 3 dB. Finally, the architecture circumvents the 2×10-4 error floor triggered by interferer-estimation errors, while its scale-invariant design enables robust generalization across arbitrary FFT sizes without retraining.