AI for Earth: Rainforest Conservation by Acoustic Surveillance
Sound
2019-08-22 v1 Databases
Machine Learning
Audio and Speech Processing
Abstract
Saving rainforests is a key to halting adverse climate changes. In this paper, we introduce an innovative solution built on acoustic surveillance and machine learning technologies to help rainforest conservation. In particular, We propose new convolutional neural network (CNN) models for environmental sound classification and achieved promising preliminary results on two datasets, including a public audio dataset and our real rainforest sound dataset. The proposed audio classification models can be easily extended in an automated machine learning paradigm and integrated in cloud-based services for real world deployment.
Cite
@article{arxiv.1908.07517,
title = {AI for Earth: Rainforest Conservation by Acoustic Surveillance},
author = {Yuan Liu and Zhongwei Cheng and Jie Liu and Bourhan Yassin and Zhe Nan and Jiebo Luo},
journal= {arXiv preprint arXiv:1908.07517},
year = {2019}
}
Comments
Accepted to KDD2019 Workshop on Data Mining and AI for Conservation