DeepASA unifies source separation, dereverberation, SED, classification, and DoAE via object-oriented processing, chain-of-inference, and temporal coherence matching, reporting SOTA on ASA2, MC-FUSS, and STARSS23.
Title resolution pending
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
-
DeepASA: An Object-Oriented Multi-Purpose Network for Auditory Scene Analysis
DeepASA unifies source separation, dereverberation, SED, classification, and DoAE via object-oriented processing, chain-of-inference, and temporal coherence matching, reporting SOTA on ASA2, MC-FUSS, and STARSS23.