.png){kind=icon}
返回
Broadband DOA Estimation Using Learning-Based Optimal Statistics Estimates
.png){kind=icon}
PRE
AI
DOI：10.1109/JSEN.2024.3505677.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
For accurate direction of arrival (DOA) estimation in challenging high reverberation and low signal-to-noise ratio (SNR) scenarios, various deep learning (DL) techniques have been developed to incorporate and enhance existing algorithms. However, addressing the challenges of enhancing network manipulability, constructing efficient learning features, and integrating algorithms in a rational manner remains a set of significant hurdles. In this article, we use DL to obtain the speech presence probability (SPP) to construct the optimal statistics estimates, which are then combined with traditional algorithms to achieve accurate DOA estimation. Specifically, we explore the application of the a posteriori SPP in DOA estimation, design a reverberation separation model for practical scenarios, and derive and validate a new computational equation for SPP under this model. Besides, we propose a frequency bin-wise network structure to improve network fitting efficiency and construct input features accordingly. Moreover, by adopting a combined structure, we avoid full-angle network feature training and instead train on partial angles under deliberate subset classification. We then evaluate the DOA estimation performance for the entire direction range with fine resolution using this approach. Simulation results demonstrate that the proposed method requires smaller datasets compared to end-to-end DL algorithms. Furthermore, the results validate that the proposed method outperforms both DL-based end-to-end approaches and traditional full-band approaches in terms of accuracy and error rate across various reverberation and SNR conditions.
Keyword:
Direction-of-arrival estimation
Estimation
Sensors
Accuracy
Feature extraction
Reverberation
Deep learning
Frequency estimation
Covariance matrices
Training
A posteriori speech presence probability (SPP)
broadband direction of arrival (DOA) estimation
deep learning (DL)
out-of-class task
statistically optimal estimation
期刊
IF:
4.5
论文数:
2.1W
被引数:
7.3W
机构
引用论文
Bearings-only target localization using total least squares使用总体最小二乘法进行仅方位目标定位.png)
SIGNAL PROCESSING
SIGNAL PROCESSINGIF3.6
PREAI
分享收藏Sparse Arrays and Sampling for Interference Mitigation and DOA Estimation in GNSSPROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏Reverberation aware deep learning for environment tolerant microphone array DOA estimationAPPLIED ACOUSTICS
APPLIED ACOUSTICSIF3.6
PREAI
分享收藏Trastuzumab-Induced Systemic Capillary Leak Syndrome in a Breast Cancer Patient曲妥珠单抗诱导的乳腺癌患者系统性毛细血管渗漏综合征
PREAI
分享收藏Paternal safety of the use of mycophenolic acid in kidney transplant recipients. Results of the EMVARON study霉酚酸在肾移植受者中使用的父方安全性。EMVARON研究的结果
PREAI
分享收藏
查看更多内容