Three-dimensional grid-free sound source localization method based on deep learning

Yunjie Zhao

doi:10.1016/j.apacoust.2024.110261

2025-01-01

PRE

DOI：10.1016/j.apacoust.2024.110261

原文链接

摘要

En 中文

Sound source localization (SSL) technology is a popular method for identifying the locations of noise sources, which serves as a prerequisite for noise control. Deep learning, as a data-driven tool, shows broad perspectives in the field of SSL with its powerful nonlinear fitting ability. The existing deep learning-based SSL methods only provide a two-dimensional (2D) representation of the sound source location and cannot obtain the specific coordinates of the sound source in three-dimensional (3D) space. Although traditional beamforming methods can be directly generalized to 3D scenes in principle, they suffer from the limitations of insufficient vertical resolution and high computational cost. Therefore, a 3D grid-free SSL method (3DGF) informed by deep learning is suggested in this study to enhance the accuracy and computational efficiency of 3D localization. First, the number of data channels is compressed to respect limited memory resources during the training process. Subsequently, a dense convolutional neural network (DenseNet) model is utilized to obtain the 3D spatial coordinates of the sound source using the processed 3D beamforming map as input. Since the coordinates are continuous and are not constrained by the grid of the beamforming map, the grid-free strategy presents more accurate localization results. Then, the effects of the volume of training data and the compression ratio are analyzed, respectively, in simulation, and the localization performance with different signal-to-noise ratios (SNRs) is also tested. Finally, by comparing 3DGF with DAMAS, both simulation and experimental results demonstrate that 3DGF improves the accuracy and efficacy of 3D localization. Meanwhile, its satisfactory generalization ability and robustness against noise highlight its potential for practical applications.

Keyword:

Sound source localization

Acoustic beamforming

Deep learning

Three-dimensional space

Dense convolutional neural network

期刊

Applied Acoustics

IF:

3.6

论文数:

7.4K

被引数:

1.7W

机构

Chongqing University

学者数:

5.1W

论文数: 4.1W

被引数: 6.0W

引用论文

A role for topoisomerase III in a recombination pathway alternative to RuvABC

Molecular Microbiology

IF0

2005-09-05

PREAI

Christopher R. Lopez; Shirley Yang; Richard W. Deibler; Starlight A. Ray; Jeanine M. Pennington; Russell J. DiGate; P. J. Hastings; Susan M. Rosenberg; E. Lynn Zechiedrich

Recreation resource assessment and monitoring techniques for mountain regions.

Tourism and development in mountain regions.

IF0

2024-04-29

PREAI

C. Monz

Fabrication and Testing Capabilities for 18650 Li/(CFx) n Cells 18650 Li/(CFx) n电池的制造和测试能力

International Journal of Electrochemical Science

IF0

2007-12-01