PK PyTorchKR Papers
Papers with Code · CC BY-SA 4.0

Lip to Speech Synthesis

Speech Recognition › Visual Speech Recognition › Lip to Speech Synthesis 14 평가 기록 8 datasets

Given a silent video of a speaker, generate the corresponding speech that matches the lip movements.

데이터셋

8개
GRID corpus (mixed-speech)Lip2Wav (Chem)Lip2Wav (Chess)Lip2Wav (DL)Lip2Wav (EH)Lip2Wav (HS)LRWTCD-TIMIT corpus (mixed-speech)