Alibaba’s Institute for Intelligent Computing has developed a new AI video generator called EMO. This technology can transform still images of faces into animated actors and singers. EMO, short for Emotive Portrait Alive, uses an audio-to-video synthesis approach to capture subtle facial motions and identity-specific nuances associated with natural speech. The system has been trained on a diverse audio-video dataset, including speeches, film and television clips, and singing performances in multiple languages. The demo videos released by Alibaba demonstrate EMO’s ability to produce convincing speaking and singing videos, significantly outperforming existing methodologies in terms of expressiveness and realism.
Go to Home
Read more at: https://mashable.com