Larger pre-training data scale and class diversity improve audio transfer learning performance, yet similarity between pre-training and target task has a stronger positive effect.
arXiv preprint arXiv:2412.11943 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
The paper introduces CoarseSoundNet, a deep learning model for classifying biophony, geophony, and anthropophony in passive acoustic monitoring recordings, reporting performance gains from additional similar data, a silence class, and decision thresholds, plus a case study on acoustic index trends.
citing papers explorer
-
How Class Ontology and Data Scale Affect Audio Transfer Learning
Larger pre-training data scale and class diversity improve audio transfer learning performance, yet similarity between pre-training and target task has a stronger positive effect.
-
CoarseSoundNet: Building a reliable model for ecological soundscape analysis
The paper introduces CoarseSoundNet, a deep learning model for classifying biophony, geophony, and anthropophony in passive acoustic monitoring recordings, reporting performance gains from additional similar data, a silence class, and decision thresholds, plus a case study on acoustic index trends.