USAD: Universal Speech and Audio Representation via Distillation
AI & ML interests
Speech and language understanding, Self-supervised learning
Distilled Audio state-space models: performance of transformers with efficiency of state-space models (https://arxiv.org/pdf/2407.04082)
-
saurabhati/DASS_medium_AudioSet_50.2
Audio Classification • 0.0B • Updated • 20 -
saurabhati/DASS_small_AudioSet_50.1
Audio Classification • 0.0B • Updated • 15 -
saurabhati/DASS_medium_AudioSet_48.9
Audio Classification • 0.0B • Updated • 4 -
saurabhati/DASS_small_AudioSet_48.6
Audio Classification • 0.0B • Updated • 32
USAD: Universal Speech and Audio Representation via Distillation
Distilled Audio state-space models: performance of transformers with efficiency of state-space models (https://arxiv.org/pdf/2407.04082)
-
saurabhati/DASS_medium_AudioSet_50.2
Audio Classification • 0.0B • Updated • 20 -
saurabhati/DASS_small_AudioSet_50.1
Audio Classification • 0.0B • Updated • 15 -
saurabhati/DASS_medium_AudioSet_48.9
Audio Classification • 0.0B • Updated • 4 -
saurabhati/DASS_small_AudioSet_48.6
Audio Classification • 0.0B • Updated • 32
datasets
0
None public yet