All the pieces are not working in concert yet, but I do not expect it to be much longer when digital technology can create on screen humans which (who?) can look human, read and comprehend better than humans, and speak with a voice indistinguishable from humans.
Adobe has both facial and voice technology which can create talking heads that look and sound like humans. In fact, the voice technology is so good that it can be programmed to sound like any human voice.
The tech, dubbed VoCo (voice conversion), presents the user with a text box. Initially the text box shows the spoken content of the audio clip. You can then move the words around, delete fragments, or type in entirely new words. When you type in a new word, there’s a small pause while the word is constructed—then you can press play and listen to the new clip.
Think of this as Photoshop for audio, a way to replicate anyone’s voice to say anything you want it to say. Now, couple that technology with another– the ability to add voice to facial reconstructions.
Researchers at Liverpool John Moore’s University have reconstructed the face of a man who lived in Dublin some 500 years ago. Incredibly accurate reconstructions like this are providing archaeologists with new way of studying the past—while also allowing them to visualize some of the most forgotten figures in history.
How far are we from digitally constructed faces that perfectly mimic humans and their speech?
Not very.
What are the implications?
A perfectly reconstructed actor could star in movies and thanks to such digital technology the onscreen persona would be indistinguishable from a human in a movie or TV show. Would there be a need for a TV news anchor if the news could be read by a digital version of a newsperson instead?
Some of the technology mentioned above has filtered down to our smartphones, via Snapchat and iPhone X’s Face ID Animoji. Matthew Hutson:
If you’ve used the smartphone application Snapchat, you may have turned a photo of yourself into a disco bear or melded your face with someone else’s. Now, a group of researchers has created the most advanced technique yet for building 3D facial models on the computer.
I see this technology going in three directions at once.
First, as a replacement for humans in media. Second, as technology to help doctors replace human body parts. Third, human-like avatars for games and devices. The pieces are there already. They have not been combined into a single, digital, human-like entity.
The next step might be marrying those components into walking talking personalized robots.
Far fetched? Not that far.