List your company
ResearchFormerly WizWand

Audio Classification on DCASE 2014

94AccuracyOur AVTS features
71.1277.068388.94Jun 30, 2018
Updated 8mo ago

Evaluation results

MethodLinks
Our AVTS featuresAuxiliary dataset=SoundNet, Auxiliary supervision=self, # auxiliary examples=2M+2018.0694
L³-NetAuxiliary dataset=SoundNet, Auxiliary supervision=self, # auxiliary examples=2M+2018.0693
Our AVTS featuresAuxiliary dataset=AudioSet, Auxiliary supervision=self, # auxiliary examples=1.8M2018.0693
Our AVTS featuresAuxiliary dataset=Kinetics, Auxiliary supervision=self, # auxiliary examples=230K2018.0691
SoundNetAuxiliary dataset=SoundNet, Auxiliary supervision=self, # auxiliary examples=2M+2018.0688
Our audio subnetAuxiliary dataset=none, Auxiliary supervision=none, # auxiliary examples=none2018.0672