Latent FxLMS: Accelerating Active Noise Control with Neural Adaptive Filters

We present a novel approach to a classic control theory problem using neural (AI-driven) adaptive filters. This work shows that machine learning techniques can accelerate convergence in cutting-edge perceptual augmentation tasks.

K. Sarkar, A. Lu, M. Mittal, Y. Zhuang, R. Corey, A. Singer, "Latent FxLMS: Accelerating Active Noise Control with Neural Adaptive Filters," arXiv preprint arXiv:2507.03854, 2025.
Download Paper