Multi-Scale Deep Feature Fusion with Machine Learning Classifier for Birdsong Classification

Birds are significant bioindicators in the assessment of habitat biodiversity, ecological impacts and ecosystem health. Against the backdrop of easier bird vocalization data acquisition, and with deep learning and machine learning technologies as the technical support, exploring recognition and classification networks suitable for bird calls has become the focus of bioacoustics research. Due to the fact that the spectral differences among various bird calls are much greater than the differences between human languages, constructing birdsong classification networks based on human speech recognition networks does not yield satisfactory results. Effectively capturing the differences in birdsong across species is a crucial factor in improving recognition accuracy. To address the differences in features, this study proposes multi-scale deep features. At the same time, we separate the classification part from the deep network by using machine learning to adapt to classification with distinct feature differences in birdsong. We validate the effectiveness of multi-scale deep features on a publicly available dataset of 20 bird species. The experimental results show that the accuracy of the multi-scale deep features on a log-wavelet spectrum, log-Mel spectrum and log-power spectrum reaches 94.04%, 97.81% and 95.89%, respectively, achieving an improvement over single-scale deep features on these three spectrograms. Comparative experimental results show that the proposed multi-scale deep feature method is superior to five state-of-the-art birdsong identification methods, which provides new perspectives and tools for birdsong identification research, and is of great significance for ecological monitoring, biodiversity conservation and forest research.