Wavelet methods improve bird song recognition in noisy environments
Processing and classifying bird songs using wavelet techniques and supervised learning
Machine Learning
Summary
Bird songs recorded in nature often get mixed with a lot of background noise, making it hard to identify species. The authors used a special wavelet technique to clean these noisy sounds efficiently. Then, they used machine learning models to classify three bird species by their songs. Their method improved the accuracy of identifying the birds, especially when using a support vector machine model. This helps in tracking invasive bird species and understanding natural environments better.
What this means in practice
- •For ecological monitoring teams: Automatically detect and classify invasive bird species from noisy natural audio recordings to support environmental management.
- •For wildlife conservation organizations: Improve species identification in large bioacoustic datasets to better monitor bird populations and biodiversity changes.
Authors
Laura Lucia Dominguez Barrios, Fidel Aniano Causil Barrios, Alex Rodrigo dos Santos Sousa, Mariana Rodrigues Motta
Abstract
This study proposes an integrated framework for the processing and classification of invasive bird species vocalizations within natural soundscapes, characterized by high levels of environmental noise. We address the challenge of signal degradation by employing a Bayesian wavelet shrinkage methodology based on the Epanechnikov kernel prior, which offers a closed form decision rule and high computational efficiency for processing large bioacoustic datasets. The methodology was applied to recordings of three species obtained from the iNaturalist platform: \textit{Euphonia violacea}, \textit{Leiothrix lutea}, and \textit{Passer domesticus}. After signal denoising, we extracted a comprehensive set of features, including Mel-Frequency Cepstral Coefficients (MFCCs) and spectral indices such as entropy and zero-crossing rate. Several supervised learning models: Random Forest, Multinomial Logistic Regression and Support Vector Machine (SVM) were evaluated across different feature dimensionalities. Our results demonstrate that the proposed wavelet based preprocessing significantly enhances classification performance, with the SVM model achieving the highest accuracy (up to 0.9398) under a 10-dimensional MFCC configuration. This research provides a robust statistical tool for automated ecological monitoring and the management of biological invasions.