List your company

Speech Recognition on Hub5'00 (SWB, CHM)

4.3SWB ScoreSystem Combination (6+7+8+9) + TrafoXL LM
4.145.226.37.38Apr 5, 2019Aug 9, 2019Dec 14, 2019Apr 18, 2020Aug 23, 2020Dec 27, 2020May 3, 2021

Evaluation results

MethodLinks
System Combination (6+7+8+9) + TrafoXL LMTraining Data=SWB-2k, External LM=LSTM+TrafoXL2021.054.36.8
Conformer Encoder-Decoder (id 9) + TrafoXL LMTraining Data=SWB-2k, Params=154M, Step Size=10ms, i-vector=false, External LM=LSTM+TrafoXL2021.054.57.2
LSTM Encoder (id 6)Training Data=SWB-2k, Params=661M, Step Size=10ms, i-vector=false, External LM=None2021.054.67.8
Conformer Encoder (id 8) + TrafoXL LMTraining Data=SWB-2k, Params=99M, Step Size=10ms, i-vector=false, External LM=LSTM+TrafoXL2021.054.67.6
Conformer Encoder (id 8)Training Data=SWB-2k, Params=99M, Step Size=10ms, i-vector=false, External LM=None2021.054.88
LSTM Encoder (id 7)Training Data=SWB-2k, Params=663M, Step Size=2.5ms, i-vector=false, External LM=None2021.054.97.7
System Combination (2+4+5) + TrafoXL LMTraining Data=SWB-300, External LM=LSTM+TrafoXL2021.05510
System Combination (1+3+5) + TrafoXL LMTraining Data=SWB-300, External LM=LSTM+TrafoXL2021.055.110.1
Conformer Encoder (id 5) + TrafoXL LMTraining Data=SWB-300, Params=68M, Step Size=10ms, i-vector=false, External LM=LSTM+TrafoXL2021.055.511.2
LSTM Encoder-Decoder (id 4)Training Data=SWB-300, Params=60M, Step Size=2.5ms, i-vector=true, External LM=LSTM+TrafoXL2021.055.711.3
Conformer Encoder (id 5) + LSTM LMTraining Data=SWB-300, Params=68M, Step Size=10ms, i-vector=false, External LM=LSTM2021.055.711.4
LSTM Encoder (id 1) + LMTraining Data=SWB-300, Params=57M, Step Size=10ms, i-vector=false, External LM=LSTM2021.055.812.1
LSTM Encoder (id 3)Training Data=SWB-300, Params=56M, Step Size=2.5ms, i-vector=true, External LM=None2021.055.911.5
LSTM Encoder (id 1)Training Data=SWB-300, Params=57M, Step Size=10ms, i-vector=false, External LM=None2021.05612
LSTM Encoder (id 2)Training Data=SWB-300, Params=61M, Step Size=10ms, i-vector=true, External LM=None2021.05612
System Combination (1+3+5)Training Data=SWB-300, External LM=None2021.056.111.9
Conformer Encoder (id 5)Training Data=SWB-300, Params=68M, Step Size=10ms, i-vector=false, External LM=None2021.056.713
LF-MMIEnd-to-end=false, Language Model=RNN2019.047.314.2
CTC + Gram-CTCEnd-to-end=true, Language Model=N-gram2019.047.314.7
Phone E2E LF-MMIEnd-to-end=true, Language Model=RNN2019.047.514.6
Jasper DR 10x5End-to-end=true, Language Model=Transformer-XL, optimizer=SGD with momentum2019.047.816.2
Char E2E LF-MMIEnd-to-end=true, Language Model=RNN2019.04817.6
RNN-TEnd-to-end=true, Language Model=4-gram2019.048.117.5
Attention Seq2SeqEnd-to-end=true2019.048.315.5
Jasper DR 10x5End-to-end=true, Language Model=4-gram, optimizer=SGD with momentum2019.048.319.3