Automatic Speech Recognition on LibriSpeech clean Speech Noise - Additive (test)
6.3WERMask2Flow-TSE
Evaluation Results
| Method | Links | |
|---|---|---|
| Mask2Flow-TSEBackbone=Whisper medium.en, Params(M)=85.32026.03 | 6.3 | |
| Mask2Flow-TSEBackbone=Whisper small.en, Params(M)=85.32026.03 | 7.6 | |
| TSELMBackbone=Whisper medium.en, Params(M)=195.42026.03 | 8.7 | |
| TSELMBackbone=Whisper small.en, Params(M)=195.42026.03 | 9.4 | |
| Metis-TSEBackbone=Whisper medium.en, Params(M)=1425.02026.03 | 9.4 | |
| Flow-onlyBackbone=Whisper medium.en, Params(M)=72.62026.03 | 9.7 | |
| Metis-TSEBackbone=Whisper small.en, Params(M)=1425.02026.03 | 10.3 | |
| Mask2Flow-TSEBackbone=Whisper base.en, Params(M)=85.32026.03 | 10.6 | |
| MaskingBackbone=Whisper medium.en, Params(M)=12.72026.03 | 11.5 | |
| TSELMBackbone=Whisper base.en, Params(M)=195.42026.03 | 12.1 | |
| Metis-TSEBackbone=Whisper base.en, Params(M)=1425.02026.03 | 12.2 | |
| Flow-onlyBackbone=Whisper small.en, Params(M)=72.62026.03 | 12.2 | |
| No preprocessingBackbone=Whisper medium.en, Params(M)=N/A2026.03 | 12.3 | |
| Mask2Flow-TSEBackbone=Whisper tiny.en, Params(M)=85.32026.03 | 13.1 | |
| TSELMBackbone=Whisper tiny.en, Params(M)=195.42026.03 | 13.8 | |
| Metis-TSEBackbone=Whisper tiny.en, Params(M)=14252026.03 | 14.3 | |
| ConVoiFilterBackbone=Whisper medium.en, Params(M)=49.92026.03 | 14.9 | |
| Flow-onlyBackbone=Whisper base.en, Params(M)=72.62026.03 | 15 | |
| MaskingBackbone=Whisper small.en, Params(M)=12.72026.03 | 15.4 | |
| ConVoiFilterBackbone=Whisper small.en, Params(M)=49.92026.03 | 17.2 | |
| Flow-onlyBackbone=Whisper tiny.en, Params(M)=72.62026.03 | 20.2 | |
| MaskingBackbone=Whisper base.en, Params(M)=12.72026.03 | 20.7 | |
| ConVoiFilterBackbone=Whisper base.en, Params(M)=49.92026.03 | 21.3 | |
| ConVoiFilterBackbone=Whisper tiny.en, Params(M)=49.92026.03 | 25.5 | |
| MaskingBackbone=Whisper tiny.en, Params(M)=12.72026.03 | 26.1 | |
| No preprocessingBackbone=Whisper small.en, Params(M)=N/A2026.03 | 28.3 | |
| No preprocessingBackbone=Whisper base.en, Params(M)=N/A2026.03 | 37.2 | |
| No preprocessingBackbone=Whisper tiny.en, Params(M)=N/A2026.03 | 51.9 |