Adaptive Representations of Sound for Automatic Insect Recognition

TL;DR

This paper explores adaptive sound representations for automatic insect recognition, demonstrating that waveform-based methods outperform spectrogram-based approaches, which could enhance biodiversity monitoring with larger datasets.

Contribution

It introduces an adaptive waveform-based feature extraction method, LEAF, showing improved classification performance over traditional spectrogram-based methods in insect sound recognition.

Findings

Waveform-based LEAF outperforms spectrogram-based methods.

Adaptive feature extraction improves classification accuracy.

Results encourage future deep learning insect monitoring applications.

Abstract

Insects are an integral part of our ecosystem. These often small and evasive animals have a big impact on their surroundings, providing a large part of the present biodiversity and pollination duties, forming the foundation of the food chain and many biological and ecological processes. Due to factors of human influence, population numbers and biodiversity have been rapidly declining with time. Monitoring this decline has become increasingly important for conservation measures to be effectively implemented. But monitoring methods are often invasive, time and resource intense, and prone to various biases. Many insect species produce characteristic mating sounds that can easily be detected and recorded without large cost or effort. Using deep learning methods, insect sounds from field recordings could be automatically detected and classified to monitor biodiversity and species distribution ranges. In this project, I implement this using existing datasets of insect sounds (Orthoptera and Cicadidae) and machine learning methods and evaluate their potential for acoustic insect monitoring. I compare the performance of the conventional spectrogram-based deep learning method against the new adaptive and waveform-based approach LEAF. The waveform-based frontend achieved significantly better classification performance than the Mel-spectrogram frontend by adapting its feature extraction parameters during training. This result is encouraging for future implementations of deep learning technology for automatic insect sound recognition, especially if larger datasets become available.