cough_012.wav
Nuria Mach, Ignasi NOU PLANA, Marie Corbin, Mariette Ducatez, Gilles Meyer, Rosa Maria Alsina-Pagès, Antonio Velarde · Recherche Data Gouv France · 2026
Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.
Recherche Data Gouv France · OpenAlex · dataset · 2026
Abstract
This repository provides access to curated data and model resources developed for the AI-based acoustic monitoring of Bovine Respiratory Disease Complex (BRDC) in calves. It supports reproducibility, benchmarking, and further research into non-invasive respiratory diagnostics. Effective management of Bovine Respiratory Disease Complex (BRDC) requires timely, non-invasive diagnostics to protect calf health and welfare, with coughing serving as a key clinical indicator. To address this objective, we deployed an AI-based acoustic monitoring system that recorded over 2,730 hours of audio during a 30-day period.
Four experimental pens, each housing seven calves and stratified by infection status and antibiotic treatment, were equipped with a dedicated microphone to enable targeted acoustic surveillance. This configuration enabled pen-specific detection of cough events, which were subsequently classified using a HuBERT-based model trained on 1,045 labeled clips. The classifier achieved 92% accuracy, reliably distinguishing coughs from non-cough events. Temporal patterns in cough event counts aligned with infection dynamics, treatment responses, and circadian patterns.
Notably, AI-detected coughs consistently preceded clinical scores by 1–2 days, confirming the system’s sensitivity to early respiratory distress. These findings support the use of acoustic surveillance as a scalable and autonomous tool for respiratory monitoring in calves.
Open the resolved locator · 10.57745/vbmp02
Metadata licence: OpenAlex metadata (CC0)