You said that?

Abstract

We present a method for generating a video of a talking face. The method takes as inputs: (i) still images of the target face, and (ii) an audio speech segment; and outputs a video of the target face lip synched with the audio. The method runs in real time and is applicable to faces and audio not seen at training time. To achieve this we propose an encoder-decoder CNN model that uses a joint embedding of the face and audio to generate synthesised talking face video frames. The model is trained on tens of hours of unlabelled videos. We also show results of re-dubbing videos using speech from a different person.

https://youtu.be/LeufDSb15Kc British Machine Vision Conference (BMVC), 2017

Cited by in corpus (13)

• VoxCeleb2: Deep Speaker Recognition
• Media Forensics and DeepFakes: an overview
• A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild
• Self-supervised learning of a facial attribute embedding from video
• End-to-End Speech-Driven Facial Animation with Temporal GANs
• Arbitrary Talking Face Generation via Attentional Audio-Visual Coherence Learning
• Talking Face Generation by Conditional Recurrent Adversarial Network
• FlexLip: A Controllable Text-to-Lip System
• Unsupervised Audiovisual Synthesis via Exemplar Autoencoders
• A Neural Lip-Sync Framework for Synthesizing Photorealistic Virtual News Anchors
• Fighting Fake News: Image Splice Detection via Learned Self-Consistency
• Dynamic Temporal Alignment of Speech to Lips
• Generating Talking Face Landmarks from Speech