Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-speaker speech recognition on WSJ0-2mix 16 kHz (test)
Loading...
14.9
WER
Conditional-Chain-Transformer
14.248
18.649
23.05
27.451
Jun 25, 2020
WER
Updated 4d ago
Evaluation Results
Method
Method
Links
WER
Conditional-Chain-Transformer
System=CTC, Training D...
2020.06
14.9
DPCL + DNN-HMM
System=HMM, Training D...
2020.06
16.5
PIT-Transformer
System=Attention-based...
2020.06
17.7
Conditional-Chain-Transformer
System=CTC, Training D...
2020.06
24.7
PIT-RNN
System=Attention-based...
2020.06
25.4
PIT-DNN-HMM
System=HMM, Training D...
2020.06
28.2
DPCL + GMM-HMM
System=HMM, Training D...
2020.06
30.8
PIT-Transformer
System=CTC, Training D...
2020.06
31.2
Feedback
Search any
task
Search any
task