Soft-label distillation from same-architecture teacher ensembles improves respiratory sound classification and sets a new ICBHI score of 64.39, though gains are partly due to test-set-based selection of settings.
Our approach effectively transferred knowledge from the ensemble of teacher models to lightweight student models, achieving state-of-the-art performance on the ICBHI dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from Ensembles
Soft-label distillation from same-architecture teacher ensembles improves respiratory sound classification and sets a new ICBHI score of 64.39, though gains are partly due to test-set-based selection of settings.