PolyChirp: Multi-Species Birdsong Classification Using TinyML on Low-Power Acoustic Sensors
2026-08-24 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors developed PolyChirp, a system that can detect multiple bird species at the same time using tiny, low-power devices. Unlike previous methods that only identified one species, PolyChirp uses smart models and special hardware to recognize up to 10 species while using very little battery power. They tested how well it works and found it is better than older methods and can run for a whole breeding season on one battery. This helps make bird monitoring in the wild more practical and efficient.
TinyMLmicrocontrollerbinary classificationmulticlass classificationneural processing unit (NPU)acoustic sensorenergy efficiencyneural architecture optimizationdataset curationwildlife monitoring
Authors
Nathan Duboisset, Zhaolan Huang, Felix Bießmann, Roudy Dagher, Antoine Lavandier, Emmanuel Baccelli
Abstract
Recent progress in the field of TinyML has demonstrated that low-power hardware based on microcontrollers can achieve bird species monitoring in real time based on acoustic sensor data for an entire breeding period on a single battery charge. However, the state of the art on low-power microcontrollers was so far limited to binary classification of a single species. In contrast, real fauna monitoring deployments often target multiple species simultaneously. To address this challenge we develop PolyChirp, an approach combining biological domain expertise, automated dataset curation, neural architecture optimization and novel hardware to achieve multiclass bird species detection in the wild. PolyChirp is based on newly designed tiny multiclass models that leverage recent microcontrollers and hardware acceleration with a neural processing unit (NPU). We evaluate the predictive performance of these models, and we measure their computational performance -- memory footprint, latency, energy consumption -- on common microcontroller hardware. Our results demonstrate that PolyChirp not only outperforms state-of-the-art on single species binary classification, but also achieves robust classification of up to 10 species simultaneously, while still fitting with the resource envelope of a sensor that must remain operational in the field for a full season on a single battery charge.