Work

Assessment of spectrogram correlation, eigensounds, and YAMNet embeddings in detecting cattle vocalizations

Year: 2026

Type: article

Abstract: Acoustic monitoring enables unattended health and welfare surveillance in Precision Livestock Farming (PLF). This study reports practical insights from developing and field-testing a prototype system at an experimental farm. We used recordings from twenty Holstein multiparous lactating dairy cows, each monitored individually in a tied stanchion barn, with temporary isolation of 4 hours post-morning milkings to facilitate data capture. We compared three approaches for automatic detection of cattle vocalisations: (1) spectrogram cross-correlation using Praat and Parselmouth, (2) an eigensounds method based on Principal Component Analysis, and (3) embedding similarity using the pre-trained YAMNet model. On a curated set of twenty 1-hour recordings collected from isolated pens, the correlation method achieved rather modest results, with only three recordings achieving an F1-score above 0.5. With suitable component counts and thresholds, the eigensounds approach yielded moderate results, with half of the recordings achieving an F1-score above 0.5, but high inter-individual variability, as adjusting thresholds improves precision for some subjects but greatly reduces recall for others. YAMNet achieved consistently high precision, with recall adjustable through thresholding and template selection, even under considerable noise. We further examine how thresholding and event capping influence precision–recall performance, and we outline a semi-automated labeling workflow, discussing the potential of wearable recorders and other strategies to enhance accuracy.

Source: Computers and Electronics in Agriculture

DOI: 10.1016/j.compag.2026.111823