List your company

English Transcription on LRS3 Noisy 0-SNR (test)

0.046WERu-HuBERT
0.03820.090850.14350.19615Jun 14, 2024

Evaluation results

MethodLinks
u-HuBERTTest Modalities=AV, Noise Dataset=LRS3†, Unlabeled Hrs (AV)=1759, Labeled Hrs (AV)=4332024.060.046
Whisper-FlamingoTest Modalities=AV, Noise Dataset=LRS3, Unlabeled Hrs (AV)=1759, Labeled Hrs (A)=680k, Labeled Hrs (AV)=4332024.060.056
AV-HuBERTTest Modalities=AV, Noise Dataset=LRS3†, Unlabeled Hrs (AV)=1759, Labeled Hrs (AV)=4332024.060.058
VIT 3DNoise Dataset=NoiseX, Labeled AV Training Hrs=90k2024.060.061
FAVA-USMTest Modalities=AV, Noise Dataset=NoiseX, Unlabeled Hrs (A)=12M, Unlabeled Hrs (AV)=5000, Labeled Hrs (AV)=4332024.060.062
FAVATest Modalities=AV, Noise Dataset=NoiseX, Unlabeled Hrs (A)=1759, Labeled Hrs (AV)=4332024.060.066
AV2vecTest Modalities=AV, Noise Dataset=MUSAN, Unlabeled Hrs (AV)=433, Labeled Hrs (AV)=4332024.060.067
AV-BEST-RQTest Modalities=AV, Noise Dataset=NoiseX, Unlabeled Hrs (AV)=1759, Labeled Hrs (AV)=4332024.060.068
Whisper-Large, Fine-tuned w/ noiseBeam search=15, Labeled AV Training Hrs=1,7592024.060.111
Whisper-Large, Fine-tuned on LRS3Test Modalities=A, Noise Dataset=LRS3, Labeled Hrs (A)=680k2024.060.117
Whisper-Large, Fine-tuned w/ noiseBeam search=15, Labeled AV Training Hrs=4332024.060.117
Whisper-Large, Fine-tuned w/ noiseBeam search=1, Labeled AV Training Hrs=1,7592024.060.119
Llama-AVSRNoise Dataset=NoiseX, Unlabeled AV Training Hrs=1,759, Labeled AV Training Hrs=4332024.060.123
Whisper-Large, Fine-tuned w/ noiseBeam search=1, Labeled AV Training Hrs=4332024.060.124
AV-HUBERTNoise Dataset=LRS3+, Unlabeled AV Training Hrs=1,759, Labeled AV Training Hrs=4332024.060.157
Adaptive AVTest Modalities=AV, Noise Dataset=MUSAN, Unlabeled Hrs (AV)=400, Labeled Hrs (A)=680k, Labeled Hrs (AV)=302024.060.163
u-HuBERTNoise Dataset=LRS3+, Unlabeled AV Training Hrs=1,759, Labeled AV Training Hrs=4332024.060.193
AV2vecNoise Dataset=MUSAN, Unlabeled AV Training Hrs=433, Labeled AV Training Hrs=4332024.060.195
Whisper-Large, Zero-shot (No Fine-Tuning)Test Modalities=A, Noise Dataset=LRS3, Labeled Hrs (A)=680k2024.060.208
Whisper-Large Zero-shotBeam search=152024.060.208
Whisper-Large, Fine-tuned w/o noiseBeam search=1, Labeled AV Training Hrs=4332024.060.216
Whisper-Large, Fine-tuned w/o noiseBeam search=15, Labeled AV Training Hrs=4332024.060.231
Whisper-Large Zero-shotBeam search=12024.060.233
Whisper-Large, Fine-tuned w/o noiseBeam search=1, Labeled AV Training Hrs=1,7592024.060.236
Whisper-Large, Fine-tuned w/o noiseBeam search=15, Labeled AV Training Hrs=1,7592024.060.241