Automatic Speech Recognition on LibriSpeech other Speech Noise - Reverb (test)
30.1WERMask2Flow-TSE
Evaluation Results
| Method | Links | |
|---|---|---|
| Mask2Flow-TSEBackbone=Whisper medium.en, Params(M)=85.32026.03 | 30.1 | |
| Flow-onlyBackbone=Whisper medium.en, Params(M)=72.62026.03 | 32.4 | |
| No preprocessingBackbone=Whisper medium.en, Params(M)=N/A2026.03 | 33.4 | |
| Mask2Flow-TSEBackbone=Whisper small.en, Params(M)=85.32026.03 | 34.7 | |
| ConVoiFilterBackbone=Whisper medium.en, Params(M)=49.92026.03 | 37.1 | |
| Flow-onlyBackbone=Whisper small.en, Params(M)=72.62026.03 | 37.2 | |
| MaskingBackbone=Whisper medium.en, Params(M)=12.72026.03 | 38.8 | |
| ConVoiFilterBackbone=Whisper small.en, Params(M)=49.92026.03 | 42 | |
| Mask2Flow-TSEBackbone=Whisper base.en, Params(M)=85.32026.03 | 42.2 | |
| Flow-onlyBackbone=Whisper base.en, Params(M)=72.62026.03 | 46.1 | |
| MaskingBackbone=Whisper small.en, Params(M)=12.72026.03 | 46.2 | |
| TSELMBackbone=Whisper medium.en, Params(M)=195.42026.03 | 49.5 | |
| Mask2Flow-TSEBackbone=Whisper tiny.en, Params(M)=85.32026.03 | 49.6 | |
| Metis-TSEBackbone=Whisper medium.en, Params(M)=1425.02026.03 | 50.6 | |
| TSELMBackbone=Whisper small.en, Params(M)=195.42026.03 | 51.6 | |
| ConVoiFilterBackbone=Whisper base.en, Params(M)=49.92026.03 | 52.1 | |
| Metis-TSEBackbone=Whisper small.en, Params(M)=1425.02026.03 | 52.9 | |
| Flow-onlyBackbone=Whisper tiny.en, Params(M)=72.62026.03 | 53.3 | |
| TSELMBackbone=Whisper base.en, Params(M)=195.42026.03 | 55.2 | |
| No preprocessingBackbone=Whisper small.en, Params(M)=N/A2026.03 | 55.9 | |
| Metis-TSEBackbone=Whisper base.en, Params(M)=1425.02026.03 | 57.6 | |
| MaskingBackbone=Whisper base.en, Params(M)=12.72026.03 | 57.7 | |
| TSELMBackbone=Whisper tiny.en, Params(M)=195.42026.03 | 58.2 | |
| Metis-TSEBackbone=Whisper tiny.en, Params(M)=14252026.03 | 58.9 | |
| ConVoiFilterBackbone=Whisper tiny.en, Params(M)=49.92026.03 | 61.1 | |
| MaskingBackbone=Whisper tiny.en, Params(M)=12.72026.03 | 65.4 | |
| No preprocessingBackbone=Whisper base.en, Params(M)=N/A2026.03 | 66.8 | |
| No preprocessingBackbone=Whisper tiny.en, Params(M)=N/A2026.03 | 89.4 |