Latent FxLMS: Accelerating Active Noise Control with Neural Adaptive Filters

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sarkar, Kanad, Lu, Austin, Mittal, Manan, Zhuang, Yongjie, Corey, Ryan, Singer, Andrew
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914345454141440
author Sarkar, Kanad
Lu, Austin
Mittal, Manan
Zhuang, Yongjie
Corey, Ryan
Singer, Andrew
author_facet Sarkar, Kanad
Lu, Austin
Mittal, Manan
Zhuang, Yongjie
Corey, Ryan
Singer, Andrew
contents Filtered-X LMS (FxLMS) is commonly used for active noise control (ANC), wherein the soundfield is minimized at a desired location. Given prior knowledge of the spatial region of the noise or control sources, we could improve FxLMS by adapting along the low-dimensional manifold of possible adaptive filter weights. We train an auto-encoder on the filter coefficients of the steady-state adaptive filter for each primary source location sampled from a given spatial region and constrain the weights of the adaptive filter to be the output of the decoder for a given state of latent variables. Then, we perform updates in the latent space and use the decoder to generate the cancellation filter. We evaluate how various neural network constraints and normalization techniques impact the convergence speed and steady-state mean squared error. Under certain conditions, our Latent FxLMS model converges in fewer steps with comparable steady-state error to the standard FxLMS.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03854
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Latent FxLMS: Accelerating Active Noise Control with Neural Adaptive Filters
Sarkar, Kanad
Lu, Austin
Mittal, Manan
Zhuang, Yongjie
Corey, Ryan
Singer, Andrew
Machine Learning
Sound
Systems and Control
Audio and Speech Processing
Adaptation and Self-Organizing Systems
Filtered-X LMS (FxLMS) is commonly used for active noise control (ANC), wherein the soundfield is minimized at a desired location. Given prior knowledge of the spatial region of the noise or control sources, we could improve FxLMS by adapting along the low-dimensional manifold of possible adaptive filter weights. We train an auto-encoder on the filter coefficients of the steady-state adaptive filter for each primary source location sampled from a given spatial region and constrain the weights of the adaptive filter to be the output of the decoder for a given state of latent variables. Then, we perform updates in the latent space and use the decoder to generate the cancellation filter. We evaluate how various neural network constraints and normalization techniques impact the convergence speed and steady-state mean squared error. Under certain conditions, our Latent FxLMS model converges in fewer steps with comparable steady-state error to the standard FxLMS.
title Latent FxLMS: Accelerating Active Noise Control with Neural Adaptive Filters
topic Machine Learning
Sound
Systems and Control
Audio and Speech Processing
Adaptation and Self-Organizing Systems
url https://arxiv.org/abs/2507.03854