Near future
No Result
View All Result
24 September 2023
  • Home
  • Tech
  • Health
  • Environment
  • Energy
  • Transports
  • Spazio
  • AI
  • concepts
  • H+
Understand, anticipate, improve the future.
CES2023 / Coronavirus / Russia-Ukraine
Near future
  • Home
  • Tech
  • Health
  • Environment
  • Energy
  • Transports
  • Spazio
  • AI
  • concepts
  • H+

Understand, anticipate, improve the future.

No Result
View All Result
Technology

A new algorithm "puts other words into the mouth" of people in videos by editing the transcription of the text.

A collaboration between technological giants allows to alter the speech in a video simply by changing the text transcription: the person in the movie changes the words and movements of the lips.

June 6 2019
Gianluca RiccioGianluca Riccio
⚪ 2 minutes
Share533Pin16Tweet46SendShare13ShareShare9
Male vlogger recording content for his video blog. Young man in focus on digital camera screen.

Male vlogger recording content for his video blog. Young man in focus on digital camera screen.

READ IN:

It's becoming extremely easy (and I don't think it's only good) to alter a video, and the latest developments in AI are truly impressive.

A collaboration between giants (Stanford and Princeton Universities plus the Max Planck Institute for Informatics and Adobe) makes it possible to alter the speech in a video simply by modifying the textual transcription, and without creating the "dubbing" effect.

In other words, the person who is speaking on video will literally change the words of his speech, also modifying the lip movements.

To achieve this somewhat disturbing result, the algorithm "learns" the phonemes and their pronunciation from the subject in the video and creates an accurate 3D model of his face, capable of replicating all sounds and movements: at that point it will be enough to edit the text of the speech and the algorithm will replace the original sentence.

The article continues after the related links

Artificial intelligence: the next evolution? From generative to interactive

AI is the new lie detector

Currently the algorithm needs at least 40 minutes of video to "train" to replicate a person in a video.

Here is a video demonstrating how the system works:

Huge ethical doubts

It is clear that this mechanism creates the possibility that anyone can modify a discourse (perhaps of political figures or public figures) by inserting elements of hatred, or disinformation, and spreading them as original and natural: this only increases concerns about the spread of systems based on deepfake.

On the other hand, there are some positive sides, and it is in the enormous savings that the editing will obtain by avoiding re-shooting entire scenes due to small pronunciation errors.

For the rest, I am sure that other "anti-counterfeiting" methods will also be developed for videos: dynamic watermarks or watermarks that make the work of artificial intelligence even more complex, in a competition between reality and manipulation that already seems destined to characterize the next years.

More info on research here

Tags: AIAlgorithmdeepfakeVideo

Latest news

  • Tesla and the new abilities of Optimus robots: "Ready for mass production"
  • EV, goodbye frequent charging: I-State promises over 1.000 km of autonomy.
  • Revolutionary generator transforms humidity into continuous electrical energy
  • All the maps of the future: from research tools to doors to tomorrow
  • The bizarre AI that translates the language of chickens
  • Jeddah Tower, construction site of the one kilometer high skyscraper reopens
  • Spider silk from modified silkworms: stronger than Kevlar and 100% natural
  • VIR-1388, HIV vaccine being tested in the USA and South Africa
  • MOWT, innovative floating hydroelectric for slow-flowing waters
  • CRAFT, what stage is the Chinese project to build an artificial Sun?


GPT Chat Megaeasy!

Concrete guide for those approaching this artificial intelligence tool, also designed for the school world: many examples of applications, usage indications and ready-to-use instructions for training and interrogating Chat GPT.

To submit articles, disclose the results of a research or scientific discoveries write to the editorial staff

Enter the Telegram channel of Futuroprossimo, click here. Or follow us on Instagram, Facebook, Twitter, Mastodon e LinkedIn.

FacebookTwitterInstagramTelegramLinkedInMastodonPinterestTikTok

The daily tomorrow.


Futuroprossimo.it provides news on the future of technology, science and innovation: if there is something that is about to arrive, here it has already arrived. FuturoProssimo is part of the network ForwardTo, studies and skills for future scenarios.

  • Environment
  • Architecture
  • Artificial intelligence
  • Gadgets
  • concepts
  • Design
  • Medicine
  • Spazio
  • Robotica
  • Work
  • Transports
  • Energy
  • Edition Francaise
  • Deutsche Ausgabe
  • Japanese version
  • English Edition
  • Portuguese Edition
  • Read more
  • Spanish edition

Subscribe to our newsletter

  • The Editor
  • Advertising on FP
  • Privacy Policy

© 2023 Near future - Creative Commons License
This work is distributed under license Creative Commons Attribution 4.0 International.

No Result
View All Result
Understand, anticipate, improve the future.
  • Home
  • Tech
  • Health
  • Environment
  • Energy
  • Transports
  • Spazio
  • AI
  • concepts
  • H+