Logo Logo
directory schraeg
Camcorders· Cinema-Kamera· Computers· GPU· Video-DSLR· accessories
Compositing· Color correction· DV Editing

Shooting· Sound
/// News
Edit the words of a speaker in a video using a text editor // Siggraph 2019

Edit the words of a speaker in a video using a text editor // Siggraph 2019

[10:19 mon,24.June 2019   by ]    

A new deepfake algorithm will soon give filmmakers and editors completely new freedom when editing clips with spoken words. If only a new take could save a scene in which an actor missed or missed a spoken word, the new post-production method would make it easy to make far-reaching changes to the spoken text.

It&s enough to just edit a transcript of the spoken text with a kind of text editor to change, delete or rearrange words - the algorithm developed by researchers at Stanford University, the Max Planck Institute for Computer Science, Princeton University and Adobe Research automatically does the rest: it synthesizes the new words with the actor&s voice and adjusts the lip movements accordingly.

A prerequisite for convincing work with the algorithm is a minimum of 40 minutes of training material from the speaker and a transcript of the spoken words (which, however, can also be generated automatically by increasingly better tools). Based on the training material, the algorithm learns which facial expressions a speaker makes when speaking each phonetic syllable and how he pronounces them - the basis for the synthetic pronunciation of new words. In tests with 138 participants, the manipulations were classified as "real" in almost 60 percent of the cases. The visual quality of the new passages is so good that it comes very close to the original, but there is still plenty of room for improvement.


In addition to the obvious benefits for professional video work, such as the subsequent modification of dialogues without new recordings, such a simple manipulation option can of course also be misused to fake videos. Although algorithms are also being developed to detect such fakes - be they images, videos or audio - to recognize, in return the fakes are becoming more and more realistic - neural networks can even be trained in interaction to produce fakes that are increasingly difficult to identify (Generative Adversarial Networks).

Link more infos at bei news.stanford.edu

deutsche Version dieser Seite: Per Texteditor die Worte eines Sprechers in einem Video verändern // Siggraph 2019

Zur Übersicht aller unserer News zur Siggraph 2019


  Vorige News lesen Nächste News lesen 
bildVimeo kündigt Unterstützung für freien AV1 Codec an bildBremst Chrome Final Cut Pro X?

related news:1E0Interesting tutorial for After Effects - virtual snow 26.January 2020
Blackmagic DaVinci Resolve 16.1.2 17.December 2019
Reading for the Holidays: Guide for DaVinci Resolve 16 Beginners 15.December 2019
BorisFX Sapphire 2020: better performance, OCIO support and new FreeLens effect 6.December 2019
SKYWATCH - Hollywood-ready SciFi short film with Blender and Kickstarter 6.December 2019
Virtual Camera - GoPro FX Reframe Plugin for Premiere Pro / After Effects 2.December 2019
Educational history lesson to accelerate After Effects 1.December 2019
alle Newsmeldungen zum Thema Compositing
1E0New Rode VideoMic NTG: Compact hybrid microphone for DSLMs, Smartphones, Boom, USB-Rec 20.November 2019
Using Youtube Audio Library is no guarantee against copyright-notices 19.November 2019
Sound Devices 888: New Portable 16-Channel Professional Mixer Recorder 3.November 2019
RØDE NTG5: New broadcast directional microphone with new acoustic design 23.October 2019
Tentacle Sync Track E audio decoder with timecode and 32-bit recording // IBC 2019 19.September 2019
Blackmagic ATEM Mini: Compact Live Production Mixer // IBC 2019 18.September 2019
Sound Devices 833: New portable professional mixer recorder // IBC 2019 13.September 2019
alle Newsmeldungen zum Thema Sound

[nach oben]

Archiv Newsmeldungen



December - November - October - September - August - July - June - May - April - March - February - January




















deutsche Version dieser Seite: Per Texteditor die Worte eines Sprechers in einem Video verändern // Siggraph 2019

last update : 26.Januar 2020 - 18:02 - slashCAM is a project by channelunit GmbH- mail : slashcam@--antispam:7465--slashcam.de - deutsche Version