A GNN plus anchor-interval framework detects abnormal respiratory sound events, reaching F1 of 22.3 percent on SPRSound, with anchor scales tuned to the observed event durations.
Graph-based audio classifica- tion using pre-trained models and graph neural networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
EZhouNet:A framework based on graph neural network and anchor interval for the respiratory sound event detection
A GNN plus anchor-interval framework detects abnormal respiratory sound events, reaching F1 of 22.3 percent on SPRSound, with anchor scales tuned to the observed event durations.