Realatars will soon be making their way to our screens

The EU-funded Content4All project set out to change content distribution and accessibility for the Deaf community through an automatic sign translation workflow with a photorealistic 3D human avatar for TV broadcasting, called Realatar, achieved through an innovative multicamera studio where the movements of real people are captured and then processed with the help of AI algorithms. The technologies used relied on advanced deep learning and machine learning algorithms. They enable a computer to observe a large amount of data and from instructions via examples they provide a desired outcome.

The innovative nature of this concept was awarded with the prestigious NAB Technology Innovation Award at the Broadcast Engineering and Information Technology Conference in 2020. Discussions from this enabled the project to launch new challenging initiatives in the field of media accessibility.

Moreover, two other projects, EASIER and SignON, will exploit and extend the Content4All project legacy, directly employing the signed collection. Furthermore Fincons Group, coordinator and lead industrial partner, is exploring concrete ways to exploit the project results for their network, like the employment of the collection of text aligned with sign language videos for research and pre-commercial purposes, and the future developments of all the algorithms for sign language recognition.