The reviewed record of science sign in
Pith

arxiv: 2409.13502 · v1 · pith:7AKKAEK7 · submitted 2024-09-20 · eess.AS · cs.SD

Neural Directional Filtering: Far-Field Directivity Control With a Small Microphone Array

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:7AKKAEK7record.jsonopen to challenge →

classification eess.AS cs.SD
keywords directivitydirectionalfilteringmicrophonesmallarraydesiredmask
0
0 comments X
read the original abstract

Capturing audio signals with specific directivity patterns is essential in speech communication. This study presents a deep neural network (DNN)-based approach to directional filtering, alleviating the need for explicit signal models. More specifically, our proposed method uses a DNN to estimate a single-channel complex mask from the signals of a microphone array. This mask is then applied to a reference microphone to render a signal that exhibits a desired directivity pattern. We investigate the training dataset composition and its effect on the directivity realized by the DNN during inference. Using a relatively small DNN, the proposed method is found to approximate the desired directivity pattern closely. Additionally, it allows for the realization of higher-order directivity patterns using a small number of microphones, which is a difficult task for linear and parametric directional filtering.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.