Speech Separation on LibriCSS Utterance-wise, Seven-channel (test)
7Hybrid ASR WER (OS)BLSTM
Evaluation Results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| BLSTMBackbone=BLSTM, Input Modality=Seven-channel2020.08 | 7 | 3.1 | 7.5 | 3.3 | 10.8 | 4.3 | 13.4 | 5.6 | 16.5 | 7.5 | 18.8 | 8.9 | |
| Conformer-largeBackbone=Conformer, Model Scale=large, Input Modality=Seven-channel2020.08 | 7.2 | 3.1 | 7.5 | 3.3 | 9.6 | 3.7 | 11.3 | 4.8 | 13.7 | 5.6 | 15.1 | 6.2 | |
| Conformer-baseBackbone=Conformer, Model Scale=base, Input Modality=Seven-channel2020.08 | 7.3 | 3.1 | 7.3 | 3.3 | 9.6 | 3.9 | 11.9 | 4.8 | 13.9 | 6 | 15.9 | 6.8 | |
| Transformer-largeBackbone=Transformer, Model Scale=large, Input Modality=Seven-channel2020.08 | 7.5 | 3.1 | 7.7 | 3.4 | 10.1 | 3.7 | 12.3 | 4.8 | 14.1 | 5.9 | 16 | 6.3 | |
| Transformer-baseBackbone=Transformer, Model Scale=base, Input Modality=Seven-channel2020.08 | 8.3 | 3.4 | 8.4 | 3.4 | 11.4 | 4.1 | 12.5 | 4.8 | 14.7 | 6.4 | 16.9 | 7.2 | |
| No separationInput Modality=Seven-channel2020.08 | 11.8 | 5.5 | 11.7 | 5.2 | 18.8 | 11.4 | 27.2 | 18.8 | 35.6 | 27.7 | 43.3 | 36.6 |