research
∙
03/14/2023
Good Neighbors Are All You Need for Chinese Grapheme-to-Phoneme Conversion
Most Chinese Grapheme-to-Phoneme (G2P) systems employ a three-stage fram...
share
research
∙
03/14/2023
DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions
For realistic talking head generation, creating natural head motion whil...
research
∙
03/22/2021
PriorityCut: Occlusion-guided Regularization for Warp-based Image Animation
Image animation generates a video of a source image following the motion...
research
∙
03/18/2021
KoDF: A Large-scale Korean DeepFake Detection Dataset
A variety of effective face-swap and face-reenactment methods have been ...
research
∙
03/09/2021
GAN Vocoder: Multi-Resolution Discriminator Is All You Need
Several of the latest GAN-based vocoders show remarkable achievements, o...
research
∙
02/16/2021