Automatic Speech Recognition on Eval2000 Fisher-Switchboard 2300-h (test)
10.9WERLF-MMI
Evaluation Results
| Method | Links | |
|---|---|---|
| LF-MMIUnit=bi-phone, LM=4-gram, RNN-LM rescoring=true2020.05 | 10.9 | |
| E2E-LF-MMIUnit=bi-phone, LM=4-gram, RNN-LM rescoring=true2020.05 | 11.1 | |
| CATUnit=mono-phone, LM=4-gram, RNN-LM rescoring=true2020.05 | 11.2 | |
| LF-MMIUnit=bi-phone, LM=4-gram, RNN-LM rescoring=false2020.05 | 11.8 | |
| AttentionUnit=char, LM=No LM, RNN-LM rescoring=false2020.05 | 11.9 | |
| E2E-LF-MMIUnit=bi-phone, LM=4-gram, RNN-LM rescoring=false2020.05 | 12 | |
| CATUnit=mono-phone, LM=4-gram, RNN-LM rescoring=false2020.05 | 12 | |
| RNN-TUnit=char, LM=4-gram, RNN-LM rescoring=false2020.05 | 12.8 | |
| E2E-LF-MMIUnit=mono-phone, LM=4-gram, RNN-LM rescoring=false2020.05 | 12.9 |