Hybrid GBT and attention-based MIL model achieves AUC 0.879 for PVH and 0.848 for NPVH on held-out test data, outperforming challenge baselines of 0.82 and 0.77.
An updated theoretical framework for vocal hyperfunction
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Chest accelerometer shows excellent agreement with microphone on fundamental frequency (ICC > 0.94) and good jitter agreement in infant cries, but lower agreement and bias for shimmer and HNR.
citing papers explorer
-
Neck-Learn: Attention-Based Multiple Instance Learning and Ensemble Framework for Ecological Momentary Assessment
Hybrid GBT and attention-based MIL model achieves AUC 0.879 for PVH and 0.848 for NPVH on held-out test data, outperforming challenge baselines of 0.82 and 0.77.
-
Cross-modal characterization of infant cry: validation of a chest-surface accelerometer in extracting acoustic vocal function measures
Chest accelerometer shows excellent agreement with microphone on fundamental frequency (ICC > 0.94) and good jitter agreement in infant cries, but lower agreement and bias for shimmer and HNR.