189 citations · 277 across the 14 of their papers we have counts for
Showing 2019 · cs.SDShow all
2 papers · 2 filters
cs.SD2019
Improving Universal Sound Separation Using Sound Classification
Efthymios Tzinis, Scott Wisdom, John R. Hershey +2
Deep learning approaches have recently achieved impressive performance on both audio source separation and sound classification. Most audio source separation approaches focus only…
cs.SD2019
Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision
Aren Jansen, Daniel P. W. Ellis, Shawn Hershey +4
Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-lab…