A system using Monte-Carlo dropout for OOD detection and contrastive novel class discovery clusters unseen raga classes from unlabeled audio with 79-81% clustering accuracy on benchmark datasets.
We first use Uncertainty Estimation for Out-of- Distribution (OOD) detection on both the Saraga and PIM datasets, effectively distinguishing unknown Ragas from known ones
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Identification and Clustering of Unseen Ragas in Indian Art Music
A system using Monte-Carlo dropout for OOD detection and contrastive novel class discovery clusters unseen raga classes from unlabeled audio with 79-81% clustering accuracy on benchmark datasets.