Automatic Speech Recognition on LibriSpeech other Speech Noise - Additive (test)
13.1WERMask2Flow-TSE
Evaluation Results
| Method | Links | |
|---|---|---|
| Mask2Flow-TSEBackbone=Whisper medium.en, Params(M)=85.32026.03 | 13.1 | |
| Mask2Flow-TSEBackbone=Whisper small.en, Params(M)=85.32026.03 | 16.1 | |
| Flow-onlyBackbone=Whisper medium.en, Params(M)=72.62026.03 | 16.2 | |
| TSELMBackbone=Whisper medium.en, Params(M)=195.42026.03 | 17.7 | |
| Metis-TSEBackbone=Whisper medium.en, Params(M)=1425.02026.03 | 18 | |
| TSELMBackbone=Whisper small.en, Params(M)=195.42026.03 | 19.5 | |
| Flow-onlyBackbone=Whisper small.en, Params(M)=72.62026.03 | 19.6 | |
| MaskingBackbone=Whisper medium.en, Params(M)=12.72026.03 | 19.8 | |
| Metis-TSEBackbone=Whisper small.en, Params(M)=1425.02026.03 | 20.4 | |
| ConVoiFilterBackbone=Whisper medium.en, Params(M)=49.92026.03 | 20.6 | |
| Mask2Flow-TSEBackbone=Whisper base.en, Params(M)=85.32026.03 | 21 | |
| No preprocessingBackbone=Whisper medium.en, Params(M)=N/A2026.03 | 22.2 | |
| TSELMBackbone=Whisper base.en, Params(M)=195.42026.03 | 24.1 | |
| ConVoiFilterBackbone=Whisper small.en, Params(M)=49.92026.03 | 24.1 | |
| Metis-TSEBackbone=Whisper base.en, Params(M)=1425.02026.03 | 24.5 | |
| Flow-onlyBackbone=Whisper base.en, Params(M)=72.62026.03 | 25.3 | |
| MaskingBackbone=Whisper small.en, Params(M)=25.32026.03 | 25.3 | |
| Mask2Flow-TSEBackbone=Whisper tiny.en, Params(M)=85.32026.03 | 27.4 | |
| TSELMBackbone=Whisper tiny.en, Params(M)=195.42026.03 | 27.5 | |
| Metis-TSEBackbone=Whisper tiny.en, Params(M)=14252026.03 | 29 | |
| ConVoiFilterBackbone=Whisper base.en, Params(M)=49.92026.03 | 31.2 | |
| Flow-onlyBackbone=Whisper tiny.en, Params(M)=72.62026.03 | 32.3 | |
| MaskingBackbone=Whisper base.en, Params(M)=12.72026.03 | 34.7 | |
| No preprocessingBackbone=Whisper small.en, Params(M)=N/A2026.03 | 38.6 | |
| ConVoiFilterBackbone=Whisper tiny.en, Params(M)=49.92026.03 | 39 | |
| MaskingBackbone=Whisper tiny.en, Params(M)=12.72026.03 | 41.8 | |
| No preprocessingBackbone=Whisper base.en, Params(M)=N/A2026.03 | 48.4 | |
| No preprocessingBackbone=Whisper tiny.en, Params(M)=N/A2026.03 | 73.8 |