List your company

Audio Recognition on Speech Commands V2

98.9AccuracyASiT
60.31670.33380.3590.367Nov 27, 2023Apr 7, 2024Aug 17, 2024Dec 28, 2024May 9, 2025Sep 18, 2025Jan 29, 2026

Evaluation results

MethodLinks
ASiT#Param=86M, Pre-training Data=AS2026.0198.9
UniRepLKNet-SType=ConvNet, Params=55.5M2023.1198.5
M2DFine-tuning=true, # Params=86M, Masking ratio=0.62024.0498.5
A-JEPA#Param=86M, Pre-training Data=AS2026.0198.5
MSM-MAEFine-tuning=true, # Params=86M, Masking ratio=0.752024.0498.4
M2DFine-tuning=true, # Params=86M, Masking ratio=0.6, Target input strategy=all patches to target2024.0498.4
M2DFine-tuning=true, # Params=86M, Masking ratio=0.7, Target input strategy=all patches to target2024.0498.4
M2DFine-tuning=true, # Params=86M, Masking ratio=0.72024.0498.4
Audio-MAEPretrain=AS-2M, Type=Transformer, Params=86.2M2023.1198.3
Audio-MAE (local)Fine-tuning=true, # Params=86M2024.0498.3
BEATsFine-tuning=true, # Params=90M, Iteration=32024.0498.3
Audio-MAE#Param=86M, Pre-training Data=AS2026.0198.3
BEATs_iter3#Param=90M, Pre-training Data=AS2026.0198.3
EAT#Param=88M, Pre-training Data=AS2026.0198.3
M2D-CLAP#Param=86M, Pre-training Data=TA+AS2026.0198.3
ASDA#Param=93M, Pre-training Data=AS2026.0198.3
CAT#Param=91M, Pre-training Data=AS2026.0198.3
SSASTFine-tuning=true, # Params=89M2024.0498.2
EAT-S/MFine-tuning=true, # Params=25.5M2024.0498.15
ASTFine-tuning=true, # Params=86M, Version=Single2024.0498.11
BEATsFine-tuning=true, # Params=90M, Iteration=3+2024.0498.1
AST#Param=86M, Pre-training Data=IN2026.0198.1
BEATs_iter3+#Param=90M, Pre-training Data=AS2026.0198.1
ATST-Frame#Param=86M, Pre-training Data=AS2026.0198.1
MAE-ASTFine-tuning=true, # Params=86M2024.0498
ATST BaseFine-tuning=true, # Params=86M2024.0498
HTS-ATFine-tuning=true, # Params=31M2024.0498
HTS-AT#Param=31M, Pre-training Data=IN2026.0198
SS-AST#Param=89M, Pre-training Data=AS+LS2026.0198
ATST-Clip#Param=86M, Pre-training Data=AS2026.0198
MAE-AST#Param=86M, Pre-training Data=AS+LS2026.0197.9
SSASTPretrain=AS-2M, Type=Transformer, Params=89.3M2023.1197.8
MaskSpecFine-tuning=true, # Params=86M2024.0497.7
MaskSpec#Param=86M, Pre-training Data=AS2026.0197.7
Meta-TransformerPretrain=LAION-2B, Type=Transformer, Params=86.6M2023.1197
CLAP#Param=86M, Pre-training Data=TA2026.0196.8
PSLAPretrain=IN-1K, Type=ConvNet2023.1196.3
PSLA#Param=14M, Pre-training Data=IN2026.0196.3
ASTPretrain=AS-2M, Type=Transformer, Params=86.9M2023.1196.2
DeLoRes-MFine-tuning=true, # Params=5.3M2024.0496
MSM-MAE#Param=86M, Pre-training Data=AS2026.0187.3
PANNSType=ConvNet2023.1161.8
PANN#Param=81M, Pre-training Data=-2026.0161.8