Researchers Develop Machine Learning System to Classify Insect Songs from Audio Recordings
Researchers have developed PULSE, a semi-supervised machine learning framework that classifies Orthoptera (crickets and grasshoppers) species from passive acoustic field recordings. The system combines weakly-supervised classification, self-supervised learning on unlabelled audio, and knowledge distillation from a general-purpose bioacoustic model. It significantly outperforms existing state-of-the-art tools and could advance large-scale, automated insect biodiversity monitoring.
A team of researchers has introduced PULSE, a multi-task semi-supervised framework designed to identify Orthoptera species — the insect order including crickets, grasshoppers, and katydids — from passive acoustic recordings. The system addresses a key limitation of current automated bioacoustic tools, which tend to be narrowly trained and difficult to transfer across contexts. PULSE integrates three complementary techniques: weakly-supervised species classification, self-supervised learning applied to unlabelled field audio, and knowledge distillation from a broader bioacoustic model. In benchmark evaluations, the domain-adapted specialist model substantially outperformed a leading general-purpose model across all metrics, achieving a macro F1 score of 0.21 versus 0.07, an AUC of 0.74 versus 0.45, and an average precision of 0.32 versus 0.19. Incorporating active learning pushed performance further, raising F1 to 0.34 and AUC to 0.84. Beyond species classification, the model's learned embeddings capture ecologically meaningful structure, which researchers have made explorable through an interactive visualisation tool. The work is accepted at the ICML 2026 Workshop on Machine Learning for Audio.
What's missing
The study does not detail the geographic scope or size of the field audio datasets used, the number of Orthoptera species covered, or how performance might degrade in highly noisy or acoustically complex environments. Generalisability to regions or species not represented in training data remains an open question.
What different sources said
- arXiv cs.AICenter
Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.