List your company

Audio-visual Speech Recognition on TED LRS3

0.009WERVGG CONFORMER
0.004440.035220.0660.09678Feb 17, 2023

Evaluation results

MethodLinks
VGG CONFORMERVisual Front-End=VGG, Encoder=CONFORMER, Train Data (Hours)=100K2023.020.009
LP CONFORMERVisual Front-End=LINEAR PROJECTION, Encoder=CONFORMER, Train Data (Hours)=100K2023.020.009
U-HUBERTVisual Front-End=RESNET, Encoder=TRANSFORMER, Train Data (Hours)=2K2023.020.012
AV-HUBERTVisual Front-End=RESNET, Encoder=TRANSFORMER, Train Data (Hours)=2K2023.020.013
VIT 3DVisual Front-End=VIT, Encoder=CONFORMER, Train Data (Hours)=90K2023.020.016
RESNET CONFORMERVisual Front-End=CONV3D+RESNET, Encoder=CONFORMER, Train Data (Hours)=0.5K2023.020.023
VGG TRANSFORMERVisual Front-End=VGG, Encoder=TRANSFORMER, Train Data (Hours)=90K2023.020.03
RNN-TVisual Front-End=CONV3D, Encoder=LSTM, Train Data (Hours)=31K2023.020.045
TM-SEQ2SEQVisual Front-End=RESNET, Encoder=TRANSFORMER, Train Data (Hours)=0.5K2023.020.08
TM-CTCVisual Front-End=RESNET, Encoder=TRANSFORMER, Train Data (Hours)=0.5K2023.020.123