Automated Speech Recognition on SlideSpeech MI
0.1104WERAdapted model (audio)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Adapted model (audio)adaptation_type=audio2026.01 | 0.1104 | 25.1 | |
| Adapted model (audio)Adaptation Modality=audio, Source Domain=DefinedAI, Tau (Specialization threshold)=0.372026.01 | 0.132 | 52.9 | |
| Ma et al.adaptation_type=text2026.01 | 0.1335 | 9.4 | |
| Text Denoising Adaptationadaptation_type=text2026.01 | 0.1343 | 8.8 | |
| Fang et al.adaptation_type=text2026.01 | 0.137 | 7 | |
| Base modeladaptation_type=none2026.01 | 0.1473 | — | |
| Text Denoising AdaptationAdaptation Modality=text, Source Domain=DefinedAI, Tau (Specialization threshold)=0.372026.01 | 0.2354 | 15.9 | |
| Ma et al.Adaptation Modality=text, Source Domain=DefinedAI, Tau (Specialization threshold)=0.372026.01 | 0.2503 | 10.6 | |
| Fang et al.Adaptation Modality=text, Source Domain=DefinedAI, Tau (Specialization threshold)=0.372026.01 | 0.2672 | 4.6 | |
| Base modelAdaptation Modality=none, Source Domain=DefinedAI, Tau (Specialization threshold)=0.372026.01 | 0.28 | — |