SMOE_DOA

Zenodo (CERN European Organization for Nuclear Research) 2026 Dataset Open access

Read full text
Authors: Wenjie Xu
DOI: 10.5281/zenodo.18286737
Cited by: 0

Abstract

# SMoE-Based DOA Estimation in Hybrid Noise Environments This repository contains the implementation of the paper "Underwater acoustic vector DOA estimation in hybrid noise environments based on sparsely-gated mixture-of-experts mechanism". ## Project Structure SMoE_DOA_Estimation/├── data_generator.py # 数据生成模块├── model.py # 模型定义├── train.py # 训练脚本├── evaluate.py # 评估脚本├── utils.py # 工具函数├── config.py # 配置文件├── requirements.txt # 依赖包└── README.md # 说明文档 # 完整的两阶段训练python train.py --stage 0 # 仅训练专家(第一阶段)python train.py --stage 1 --expert 0 # 仅训练门控网络(第二阶段)python train.py --stage 2 python evaluate.py

Fields of Study & Subjects

Direction-of-Arrival Estimation Techniques Underwater Vehicles and Communication Systems Speech and Audio Processing

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
18 January 2026
Document type
Dataset