2024/07/31 by Zhaolan Huang, Adrien Tousnakhoff, Huang, Zhaolan +13 · 4 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Animal Vocal Communication and Behavior #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Music and Audio Processing #Signal Processing (eess.SP) #Sound (cs.SD) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2407.21453
openalex publication_date 2024/07/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Monitoring biodiversity at scale is challenging. Detecting and identifying species in fine grained taxonomies requires highly accurate machine learning (ML) methods. Training such models requires large high quality data sets. And deploying these models to low power devices requires novel compression techniques and model architectures. While species classification methods have profited from novel data sets and advances in ML methods, in particular neural networks, deploying these state of the art models to low power devices remains difficult. Here we present a comprehensive empirical comparison of various tinyML neural network architectures and compression techniques for species classification. We focus on the example of bird song detection, more concretely a data set curated for studying the corn bunting bird species. The data set is released along with all code and experiments of this study. In our experiments we compare predictive performance, memory and time complexity of classical spectrogram based methods and recent approaches operating on raw audio signal. Our results indicate that individual bird species can be robustly detected with relatively simple architectures that can be readily deployed to low power devices.