Automatic Speech Recognition on Hub5 2000 (test)
4.7WER (SWB)Single headed attention based sequence-to-sequence model
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Single headed attention based sequence-to-sequence modelTraining Data=2k-lrg, External Language Model=true, Cross-utterance=true2020.01 | 4.7 | 7.8 | |
| Single headed attention based sequence-to-sequence modelTraining Data=2k-lrg, External Language Model=false, Cross-utterance=false2020.01 | 4.8 | 8 | |
| Single headed attention based sequence-to-sequence modelTraining Data=2k, External Language Model=true, Cross-utterance=false2020.01 | 5.5 | 9.8 | |
| Single headed attention based sequence-to-sequence modelTraining Data=2k, External Language Model=true, Cross-utterance=true2020.01 | 5.6 | 9.5 | |
| Single headed attention based sequence-to-sequence modelTraining Data=2k, External Language Model=false, Cross-utterance=false2020.01 | 5.9 | 10.2 | |
| Single headed attention based sequence-to-sequence modelTraining Data=300h, External Language Model=true, Cross-utterance=true2020.01 | 6.4 | 12.5 | |
| Single headed attention based sequence-to-sequence modelTraining Data=300h, External Language Model=true, Cross-utterance=false2020.01 | 6.5 | 13 | |
| Single headed attention based sequence-to-sequence modelTraining Data=300h, External Language Model=false, Cross-utterance=false2020.01 | 7.6 | 14.6 |