Automatic Speech Recognition on CHiME-4 (test)
4.82WERUADF
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| UADFNoise Type=ped2024.02 | 4.82 | 12.2 | — | — | — | — | — | — | |
| StaticNoise Type=ped2024.02 | 4.96 | 9.8 | — | — | — | — | — | — | |
| StaticNoise Type=str2024.02 | 5.28 | 9.9 | — | — | — | — | — | — | |
| UADFNoise Type=str2024.02 | 5.28 | 9.9 | — | — | — | — | — | — | |
| GERNoise Type=ped2024.02 | 5.49 | — | — | — | — | — | — | — | |
| GERNoise Type=str2024.02 | 5.86 | — | — | — | — | — | — | — | |
| UADFNoise Type=Avg.2024.02 | 6.08 | 9.9 | — | — | — | — | — | — | |
| StaticNoise Type=Avg.2024.02 | 6.17 | 8.6 | — | — | — | — | — | — | |
| UADFNoise Type=caf2024.02 | 6.22 | 10.6 | — | — | — | — | — | — | |
| StaticNoise Type=caf2024.02 | 6.37 | 8.5 | — | — | — | — | — | — | |
| GERNoise Type=Avg.2024.02 | 6.75 | — | — | — | — | — | — | — | |
| GERNoise Type=caf2024.02 | 6.96 | — | — | — | — | — | — | — | |
| ClozeGERBackbone=LLaMA-2-7b, Source Speech=false, LoRA=true, Logits Calibration=true, Post-processing=true2024.05 | 7 | — | — | — | — | — | — | 25.5 | |
| ClozeGERBackbone=SpeechGPT, Source Speech=true, LoRA=true, Logits Calibration=true, Post-processing=true2024.05 | 7.1 | — | — | — | — | — | — | 24.5 | |
| UADFNoise Type=bus2024.02 | 7.98 | 8 | — | — | — | — | — | — | |
| StaticNoise Type=bus2024.02 | 8.05 | 7.2 | — | — | — | — | — | — | |
| GERNoise Type=bus2024.02 | 8.67 | — | — | — | — | — | — | — | |
| Whisper Baseline2024.05 | 9.4 | — | — | — | — | — | — | — | |
| ASR-onlyNoise Type=ped2024.02 | 11.36 | — | — | — | — | — | — | — | |
| ASR-onlyNoise Type=caf2024.02 | 11.48 | — | — | — | — | — | — | — | |
| ASR-onlyNoise Type=Avg.2024.02 | 11.89 | — | — | — | — | — | — | — | |
| ASR-onlyNoise Type=str2024.02 | 12.28 | — | — | — | — | — | — | — | |
| ASR-onlyNoise Type=bus2024.02 | 12.45 | — | — | — | — | — | — | — |