New methods improve respiratory sound classification

Arxiv CS.SD (Sound/Audio ML)

Lung-SRAD uses dual-axis patch-mix contrastive learning and spectral-aware regularization. QLung introduces quality-adaptive angular margin learning to improve feature generalization.

See 2 more sources

Lung-SRAD: Spectral-Aware Regularized Audio DASS with Dual-Axis Patch-Mix Contrastive Learning for Respiratory Sound Classification3 days agoHemansh Shridhar, Miika Toikkanen, June-Woo Kim

Quality Adaptive Angular Margin Learning for Respiratory Sound Classification3 days agoYoon Tae Kim, Heejoon Koo, Miika Toikkanen, June-Woo Kim

Arxiv CS.SD (Sound/Audio ML)·Ziqi MaMengyu HanAnteng CaiZhanchong LiuBowen FengHang YuSheng Hu

3 days ago