2 papers
cs.SD2026
MADS: A Multiview Acoustic Descriptor Set Beyond Standard Spectral Summaries
Utsab Ghosh, Roshni Chakraborty
Dominant audio classification pipelines rely either on compact handcrafted summaries or on fixed time-frequency frontends such as log-mel representations prior to deep modeling. Wh…
cs.AI2026
When Features Become Instances: Inverted Contrastive Learning for Unsupervised Feature Selection
Utsab Ghosh, Roshni Chakraborty
Unsupervised feature selection seeks a compact subset of informative features without access to class labels, making feature utility difficult to define. Existing UFS methods there…