Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Computer Vision
/
Lip to Speech Synthesis
Lip to Speech Synthesis
24 benchmarks
13 papers
Given a silent video of a speaker, generate the corresponding speech that matches the lip movements.
Benchmarks
Lip to Speech Synthesis on
GRID corpus (mixed-speech)
ESTOI
PESQ
STOI
Lip to Speech Synthesis on
Lip2Wav (Chem)
ESTOI
PESQ
STOI
Lip to Speech Synthesis on
Lip2Wav (Chess)
ESTOI
PESQ
STOI
Lip to Speech Synthesis on
Lip2Wav (DL)
ESTOI
PESQ
STOI
Lip to Speech Synthesis on
Lip2Wav (EH)
ESTOI
PESQ
STOI
Lip to Speech Synthesis on
Lip2Wav (HS)
ESTOI
PESQ
STOI
Lip to Speech Synthesis on
LRW
ESTOI
PESQ
STOI
Lip to Speech Synthesis on
TCD-TIMIT corpus (mixed-speech)
ESTOI
PESQ
STOI