A Convolutional Neural Network and R-Shiny App for Automated Identification and Classification of Animal Sounds

Abstract

The use of passive acoustic monitoring in wildlife ecology has increased dramatically in recent years as researchers take advantage of improvements in automated recording units and associated technologies. These technologies have allowed researchers to collect large quantities of acoustic data which must then be processed to extract meaningful information, e.g. target species detections. A persistent issue in acoustic monitoring is the challenge of processing these data most efficiently to automate the detection of species of interest, and deep learning has emerged as a powerful approach to achieve these objectives. Here we report on the development and use of a deep convolutional neural network for the automated detection of 14 forest-adapted species by classifying spectrogram images generated from short audio clips. The neural network has improved performance compared to models previously developed for some of the target classes. Our neural network performed well for most species and at least satisfactory for others. To improve portability and usability by field biologists, we developed a graphical interface for the neural network that can be run through RStudio using the Shiny package, creating a highly portable solution to efficiently process audio data closer to the point of collection and with minimal delays using consumer-grade computers.

The development of a convolutional neural network for the automatic detection of Northern Bobwhite Colinus virginianus covey calls

“…The recent growth and popularity in machine learning methods has contributed most significantly to improvements in automatic call detection through the development of deep convolutional neural networks (CNNs) for acoustic analysis (Stowell, 2022). These models, most commonly used in image and speech recognition (Kim, 2017; Nassif et al., 2019; Rawat & Wang, 2017), show great potential for acoustic processing and have been applied successfully to a wide variety of aquatic and terrestrial acoustic recognition research problems (Dufourq et al., 2021; Gupta et al., 2021; Ruff et al., 2020a; Stowell et al., 2018; Zhong et al., 2020). One way in which CNNs increase detection success and reduce overfitting is through data augmentation (Li et al., 2017).…”