Tasks
SotA
Datasets
Papers
Methods
Submit
About
Datasets
/
LRS3
LRS3
Benchmarks
10-shot image generation
/
FID
10-shot image generation
/
LSE-C
10-shot image generation
/
LSE-D
3D
/
FID
3D
/
LSE-C
3D
/
LSE-D
3D Face Modelling
/
FID
3D Face Modelling
/
LSE-C
3D Face Modelling
/
LSE-D
3D Face Reconstruction
/
FID
3D Face Reconstruction
/
LSE-C
3D Face Reconstruction
/
LSE-D
Face Generation
/
FID
Face Generation
/
LSE-C
Face Generation
/
LSE-D
Face Reconstruction
/
FID
Face Reconstruction
/
LSE-C
Face Reconstruction
/
LSE-D
Facial Recognition and Modelling
/
FID
Facial Recognition and Modelling
/
LSE-C
Facial Recognition and Modelling
/
LSE-D
Image Generation
/
FID
Image Generation
/
LSE-C
Image Generation
/
LSE-D
Speech Separation
/
SI-SNRi
Speech Separation
/
SDRi
Talking Head Generation
/
FID
Talking Head Generation
/
LSE-C
Talking Head Generation
/
LSE-D
Related Benchmarks
LRS3+VGGSound
/
Speech Denoising
/
CBAK
LRS3+VGGSound
/
Speech Denoising
/
COVL
LRS3+VGGSound
/
Speech Denoising
/
CSIG
LRS3+VGGSound
/
Speech Denoising
/
PESQ
LRS3+VGGSound
/
Speech Denoising
/
STOI
LRS3-TED
/
Active Speaker Detection
/
Accuracy
LRS3-TED
/
Audio-Visual Speech Recognition
/
Word Error Rate (WER)
LRS3-TED
/
Automatic Speech Recognition (ASR)
/
WER
LRS3-TED
/
Automatic Speech Recognition (ASR)
/
Word Error Rate (WER)
LRS3-TED
/
Keyword Spotting
/
Top-1 Accuracy
LRS3-TED
/
Keyword Spotting
/
Top-5 Accuracy
LRS3-TED
/
Keyword Spotting
/
mAP
LRS3-TED
/
Keyword Spotting
/
mAP IOU@0.5
LRS3-TED
/
Lipreading
/
Word Error Rate (WER)
LRS3-TED
/
Natural Language Transduction
/
Word Error Rate (WER)
LRS3-TED
/
Speech Recognition
/
WER
LRS3-TED
/
Speech Recognition
/
Word Error Rate (WER)
LRS3-TED
/
Visual Speech Recognition
/
Word Error Rate (WER)