Reproduce “Sound event localization and classification using WASN in Outdoor Environment” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Dongzhe Zhang, Jianfeng Chen, Jisheng Bai, Mou Wang, Dongyuan Shi, Qixiang Niu, Alberto Bernardini

The authors combine multiple microphone-array views to identify and locate a target sound. Each array contributes spatial-energy soundmaps, auditory-inspired time-frequency features, and node position; a neural network predicts class and coordinates jointly. The method averages 0.957 SELC on three held-out simulated areas, versus 0.947 for CNN-STFT, and scores 0.946 in a park experiment, with evidence limited to tested simulations and one field setup.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.