A comparator loss trains speech models to produce ordinal severity scores for NDD progression that distinguish patients from controls and correlate with unseen clinical annotations.
Ensemble of deep neural network models for MOS prediction,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Comparator Loss: An Ordinal Contrastive Loss to Derive a Severity Score for Speech-based Health Monitoring
A comparator loss trains speech models to produce ordinal severity scores for NDD progression that distinguish patients from controls and correlate with unseen clinical annotations.