Label Interpolation Based Deep Learning for Direction of Arrival Estimation

Shiwei Ren, Dingsu Xu, Weijiang Wang*

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

In this paper, an end-to-end framework is proposed for direction of arrival (DOA) estimation on the conditions of anechoic and low SNR environments via Deep Learning (DL). Spectrum labels generated by interpolation methods are used for regressors attainment in the training of neural networks. When the regressors converge properly, a peak finding strategy is proposed to estimate DOAs more precisely, which consists of the Gaussian smoothing, rough sampling and Least Squares method. Numerical experiments prove that this framework performs better than the existing DL methods.

源语言英语
主期刊名Proceedings - 2021 7th Annual International Conference on Network and Information Systems for Computers, ICNISC 2021
出版商Institute of Electrical and Electronics Engineers Inc.
937-943
页数7
ISBN(电子版)9781665402323
DOI
出版状态已出版 - 2021
活动7th Annual International Conference on Network and Information Systems for Computers, ICNISC 2021 - Virtual, Guiyang, 中国
期限: 23 7月 202125 7月 2021

出版系列

姓名Proceedings - 2021 7th Annual International Conference on Network and Information Systems for Computers, ICNISC 2021

会议

会议7th Annual International Conference on Network and Information Systems for Computers, ICNISC 2021
国家/地区中国
Virtual, Guiyang
时期23/07/2125/07/21

指纹

探究 'Label Interpolation Based Deep Learning for Direction of Arrival Estimation' 的科研主题。它们共同构成独一无二的指纹。

引用此