This work builds on a previous AI-enabled approach utilizing autoregressive transformer-based models by adding a Finite Scalar Quantization (FSQ) tokenizer layer which aims to improve the interference rejection performance while keeping overall latency to a minimum.
Abstract
AI-based structured interference rejection has grown more popular because deep learning approaches can outperform traditional methods by jointly considering the signal of interest (SOI) and the signal mixture (SOI plus interference). This work builds on a previous AI-enabled approach utilizing autoregressive transformer-based models by adding a Finite Scalar Quantization (FSQ) tokenizer layer which aims to improve the interference rejection performance while keeping overall latency to a minimum. Additionally, we experiment with other inference optimization techniques with the goal of speeding up inference without much accuracy loss. We explore this space with an experiment where the SOI is a digitally modulated radio frequency (RF) signal and the structured interference is a digital television signal, an extremely common type of Orthogonal Frequency-Division Multiplexing (OFDM) transmission. Our results achieve low latency and increased interference rejection over traditional techniques and prior work with other AI-enabled methods. We demonstrate the benefits of the AI-enabled approaches via audio metrics such as Perceptual Evaluation of Speech Quality (PESQ). Additionally, we explore a variety of applications and detail how our interference rejection algorithm may be used in operationally-relevant scenarios.
In this paper, we study measurement-driven signal-to-interference-plus-noise ratio (SINR) maximization for a multi-reconfigurable intelligent surface (RIS)-aided single-input single-output (SISO) system with unknown strong interference sources. Specifically, the objective is to optimize the reflection coefficients such that the SINR is maximized at the receiver. As the interference channels are unknown, such an optimization problem is a black-box optimization problem with an objective function whose closed-form analytical expression is unknown. To address the high-dimensional black-box optimization problem with discrete variable constraints, we introduce a group-based phase parameterization that significantly reduces the search dimension. Building on this model, we develop a group-based zeroth-order adaptive moment (ZO-AdaMM) algorithm. Simulation results show that the proposed grouping strategy markedly accelerates the convergence speed and achieves a superior interference suppression performance under limited measurement budgets, especially in the small-budget regime.
Binyao Ma, Peilan Wang, Bin Wang et al.· 0 citations
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 ($\text{SIR}{=}{-}10$ 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 ($\text{SIR}{=}10$ 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 $2{\times}10^{-4}$ error floor triggered by interferer-estimation errors, while its scale-invariant design enables robust generalization across arbitrary FFT sizes without retraining.
E. Kavvousanos, F. Catthoor, Vassilis Paliouras· 0 citations
The rapiddevelopment of frequency-modulated continuous wave (FMCW) radar has introduced critical mutual interference challenges. Currently, compressed sensing (CS) and deep learning offer promising interference suppression capabilities, while conventional CS implementations face computational bottlenecks and hyperparameter dependence. Meanwhile, the limited interpretability and generalization ability of generic deep networks are also concerns. To address these issues, a learning-based flexible dual-path iterative network (LFDPI-Net) is proposed for suppressing interference between FMCW radars. First, the interference suppression is transformed into model-driven optimization. Second, it combines the interpretability of CS-based methods with feature extraction of deep learning, using a designed mirrored convolutional neural network to perform nonlinear mapping to the target, thereby expanding the receptive field. To enhance generalization, the model flexibly learns hyperparameters in a layered manner. In addition, LFDPI-Net is devised as a dual-path feedforward model to better synchronize the processing of multiple complex-valued pulses. Finally, a multidomain joint constraint term is proposed to stabilize the optimization process by simultaneously considering both target and interference signals. A series of experiments demonstrate that LFDPI-Net can efficiently suppress interference and accurately extract target information, offering a practical solution to mutual interference in dense FMCW radar scenarios.
Hao Zhang, Shunjun Wei, Rui Min et al.· IEEE Transactions on Aerospa...· 0 citations
With the rapid development of information technology, communication systems are increasingly required to support stable, reliable, and real-time information transmission in complex environments. However, during practical communication transmission, signals are often affected by noise interference, channel fading, network jitter, multi-user interference, and packet loss. These problems may reduce speech intelligibility, increase bit error rates, cause video freezing, and weaken the continuity and reliability of communication services. Traditional enhancement techniques rely on stationary assumptions or fixed redundancy, and thus perform poorly under non-stationary noise or dynamically fluctuating network conditions. In recent years, deep learning-based methods have shown strong potential in learning nonlinear mappings from degraded to clean signals, offering better adaptability to diverse distortions. Nevertheless, the analysis shows that AI technology still faces practical deployment challenges, including high computational complexity, heavy dependence on large-scale labeled training data, and limited cross-scenario generalization capability, which require further optimization before such approaches can be reliably integrated into real-time audio/video communication systems.
Jiantao Hu· Applied and Computational En...· 0 citations
These proposed CGGN16 student AEC models show significantly less near-end speech distortion at only 2% of its teacher's computational complexity, surpass the overall performance of a six times more complex model trained on ground-truth labels, and outperform other AEC-focused architectures from recent literature.
Ernst Seidel, Pejman Mowlaee, Tim Fingscheidt· 0 citations
This letter proposes GC-SQMCC, a computationally efficient robust adaptive filtering algorithm tailored for fixed-point acoustic echo cancellation (AEC) under impulsive noise. Departing from signal-driven quantizers, the proposed scheme synergistically aligns a nonlinear compression-mapping quantizer with the influence function of the generalized Cauchy (GC) kernel, allocating fine resolution near zero and gracefully coarsening for large impulses. An adaptive error envelope tracker (AEET) normalizes the dynamic range online, while a synergistic look-up table (LUT) fuses the kernel weighting and error scaling into a single memory access, enabling 16-bit integer arithmetic during the per-sample filtering stage by moving divisions and transcendental operations to the infrequent LUT-update process. A threshold-based adaptive LUT update (ALUT-U) further decouples high-frequency filtering from low-frequency grid adjustment. Mean and mean-square stability conditions are derived, and an asymptotic steady-state MSD is derived under high-resolution assumptions. Simulations on AEC under single-talk and double-talk scenarios show that GC-SQMCC achieves lower steady-state MSD than competing quantized baselines under various configurations.
Ming Fang, Yingying Zhu, Yingsong Li et al.· IEEE Signal Processing Lette...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
