Neural Directional Filtering Using a Compact Microphone Array

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Huang, Weilong, Chetupalli, Srikanth Raj, Halimeh, Mhd Modar, Thiergart, Oliver, Habets, Emanuël A. P.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912978195972096
author Huang, Weilong
Chetupalli, Srikanth Raj
Halimeh, Mhd Modar
Thiergart, Oliver
Habets, Emanuël A. P.
author_facet Huang, Weilong
Chetupalli, Srikanth Raj
Halimeh, Mhd Modar
Thiergart, Oliver
Habets, Emanuël A. P.
contents Beamforming with desired directivity patterns using compact microphone arrays is essential in many audio applications. Directivity patterns achievable using traditional beamformers depend on the number of microphones and the array aperture. Generally, their effectiveness degrades for compact arrays. To overcome these limitations, we propose a neural directional filtering (NDF) approach that leverages deep neural networks to enable sound capture with a predefined directivity pattern. The NDF computes a single-channel complex mask from the microphone array signals, which is then applied to a reference microphone to produce an output that approximates a virtual directional microphone with the desired directivity pattern. We introduce training strategies and propose data-dependent metrics to evaluate the directivity pattern and directivity factor. We show that the proposed method: i) achieves a frequency-invariant directivity pattern even above the spatial aliasing frequency, ii) can approximate diverse and higher-order patterns, iii) can steer the pattern in different directions, and iv) generalizes to unseen conditions. Lastly, experimental comparisons demonstrate superior performance over conventional beamforming and parametric approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2511_07185
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Directional Filtering Using a Compact Microphone Array
Huang, Weilong
Chetupalli, Srikanth Raj
Halimeh, Mhd Modar
Thiergart, Oliver
Habets, Emanuël A. P.
Audio and Speech Processing
Beamforming with desired directivity patterns using compact microphone arrays is essential in many audio applications. Directivity patterns achievable using traditional beamformers depend on the number of microphones and the array aperture. Generally, their effectiveness degrades for compact arrays. To overcome these limitations, we propose a neural directional filtering (NDF) approach that leverages deep neural networks to enable sound capture with a predefined directivity pattern. The NDF computes a single-channel complex mask from the microphone array signals, which is then applied to a reference microphone to produce an output that approximates a virtual directional microphone with the desired directivity pattern. We introduce training strategies and propose data-dependent metrics to evaluate the directivity pattern and directivity factor. We show that the proposed method: i) achieves a frequency-invariant directivity pattern even above the spatial aliasing frequency, ii) can approximate diverse and higher-order patterns, iii) can steer the pattern in different directions, and iv) generalizes to unseen conditions. Lastly, experimental comparisons demonstrate superior performance over conventional beamforming and parametric approaches.
title Neural Directional Filtering Using a Compact Microphone Array
topic Audio and Speech Processing
url https://arxiv.org/abs/2511.07185