Npvforensics: Jointing non-critical phonemes and visemes for deepfake detection

Y Chen, Y Yu, R Ni, Y Zhao, H Li - arXiv preprint arXiv:2306.06885, 2023 - arxiv.org
Deepfake technologies empowered by deep learning are rapidly evolving, creating new
security concerns for society. Existing multimodal detection methods usually capture audio …

[PDF][PDF] RAST: A Reference-Audio Synchronization Tool for Dubbed Content

D Meyer, E Abecassis… - Proc. Interspeech …, 2024 - isca-archive.org
In the film industry, audio-video synchronization issues are considered major quality defects
and key drivers of viewer disengagement. This is especially true for dubbed content, which …

Enabling Global Communication through Automated Real-Time Video Dubbing

K Priya, M Maanesh - 2023 IEEE Technology & Engineering …, 2023 - ieeexplore.ieee.org
In today's digital age, the demand for online video content is skyrocketing. However,
reaching a diverse, multilingual audience poses a significant challenge due to language …