Concept bottleneck and concept embedding models, trained on clinical concepts extracted from patient notes by a large language model, detect voice pathology from audio almost as accurately as an end-to-end transformer.
In: Advances in Neural Infor- mation Processing Systems (NeurIPS)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Concept-based approach to Voice Disorder Detection
Concept bottleneck and concept embedding models, trained on clinical concepts extracted from patient notes by a large language model, detect voice pathology from audio almost as accurately as an end-to-end transformer.