Deep Learning-Based Acoustic Mosquito Detection in Noisy Conditions Using Trainable Kernels and Augmentations

TL;DR

This paper presents a deep learning approach with trainable kernels and data augmentations for robust mosquito detection in noisy audio environments, significantly outperforming baseline methods.

Contribution

It introduces a novel fusion of pre-processing and deep learning that accelerates training and inference, achieving state-of-the-art results in noisy conditions.

Findings

Outperforms baseline by 212% on test set

Provides reliable mosquito detection in noisy environments

Demonstrates effective hyper-parameter optimization during training

Abstract

In this paper, we demonstrate a unique recipe to enhance the effectiveness of audio machine learning approaches by fusing pre-processing techniques into a deep learning model. Our solution accelerates training and inference performance by optimizing hyper-parameters through training instead of costly random searches to build a reliable mosquito detector from audio signals. The experiments and the results presented here are part of the MOS C submission of the ACM 2022 challenge. Our results outperform the published baseline by 212% on the unpublished test set. We believe that this is one of the best real-world examples of building a robust bio-acoustic system that provides reliable mosquito detection in noisy conditions.