期刊
APPLIED ACOUSTICS
卷 197, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.apacoust.2022.108918
关键词
Source localization; direction finding; single -sensor; Single -site; Manifold learning; Diffusion maps; Passive sensing; Position finding; Non -cooperative localization
类别
资金
- Israel Science Foundation
This paper introduces a supervised method for estimating the location and velocity of a moving acoustic source using a single microphone based on manifold learning. The algorithm is sensitive to variations in the speed of the sources and performs well in reverberant and noisy environments, but is sensitive to changes in environmental conditions.
Source localization is a common problem in various fields and has applications in both military and civil sectors. Localization of acoustic sources generally requires a few microphones, but it is also possible to use a single microphone and data that was prerecorded in the same environment. Unfortunately, existing single-microphone localization methods are restricted to acoustic sources that have a fixed location. In this paper, we introduce a supervised method for estimating both the location and velocity of a moving acoustic source, using a single microphone based on a manifold learning approach. Simulation results demonstrate the sensitivity of the algorithm to variations in the speed of the sources, resulting in a trade-off between the accuracy of the estimated location and the accuracy of the estimated direction. In addi-tion, the results demonstrate the sensitivity to variations in direction and frame length of the received signal. The algorithm performs well in reverberant and noisy environments, yet is sensitive to environ-mental conditions changes.(c) 2022 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据