Adobe is working on a new piece of software that would act like a Photoshop for audio, according to Adobe developer Zeyu Jin, who spoke at the Adobe MAX conference in San Diego, California today. The software is codenamed Project VoCo, and it’s not clear at this time when it will materialize as a commercial product. The standout feature, however, is the ability to add words not originally found in the audio file.

An Adobe representative confirmed the project’s existence to The Verge, clarifying that it was shown off today as part of a sneak peak program at the MAX conference. The project is currently in development as part of a collaboration between members of Adobe Research and Princeton University. News of Project VoCo was first reported by the art and design website Creative Bloq earlier today.

Like Photoshop, Project VoCo is designed to be a state-of-the-art audio editing application. Beyond your standard speech editing and noise cancellation features, Project VoCo can also apparently generate new words using a speaker’s recorded voice. Essentially, the software can understand the makeup of a person’s voice and replicate it, so long as there’s about 20 minutes of recorded speech. In Jin’s demo, the developer showcased how Project VoCo let him add a word to a sentence in a near-perfect replication of the speaker, according to Creative Bloq.



"When recording voiceovers, dialog, and narration, people would often like to change or insert a word or a few words due to either a mistake they made or simply because they would like to change part of the narrative," reads an official Adobe statement. "We have developed a technology called Project VoCo in which you can simply type in the word or words that you would like to change or insert into the voiceover. The algorithm does the rest and makes it sound like the original speaker said those words."

So similar to how Photoshop ushered in a new era of editing and image creation, this tool could transform how audio engineers work with sound, polish clips, and clean up recordings and podcasts. Of course, there’s all sorts of ethical implications involved when we have the ability to falsify entire sentences using a person’s voice. But just as Photoshop taught the general public to be wary of suspect images, Project VoCo might do so the same with regards to doctored audio clips.

http://www.theverge.com/2016/11/3/13514088/adobe-photoshop-audio-project-voco

 

Cool, some Mission Impossible shit right there

 

We already have Photoshop for audio. Melodyne.

 

Apparently this one is starting where Melodyne stops.

 

1) Celemony (Melodyne) never stops.
2) Voice actors and voice recognition security system developers going "WTFFFfF?!"
3)"And ur I kissed my Jorda"!!!
4) ?????????
5) PROFIT!!!1!!

 

I might be the only one that thinks it is too creepy. We already have issues telling a real photo from a "photoshopped" one. Now you can record a speech of, say, Obama, and letting him say "Germany sucks and I will destroy it". Disaster! And where will it end? The time when we can't seperate the real world from the illusion anymore will be a nightmare!

 

lol..... Great for crime.....

 

Exactly my line of thinking after reading the info before even seeing your comment. This could have some legitimate good uses, but oh, the misuses that will follow by the evil idiots out there...
Someone who didn't really say something will have little defense, and someone who really did say something can say, "Oh, that was just Vocoed. Not really me."
So looks like a follow up program will have to be a "Voco detector."

 

They gonna call it Vocoshop. LOL

 

I'd rather say Izotope RX or Sony's layers (can't recall the name now) , both of them have brushes and you select a portion of the spectrum and remove it, enhance it , polish it etc.It's my daytime job.
But this thing Adobe presents here is creepy.It's like a knife.You could use it to cut bread, or someone's head.

 

rt pls.

 

And solving crime, imagine how creative you could get editing those confessions

 

Last edited: Nov 4, 2016

= Audition?

 

A software like this one should just be forbidden.

Photoshop+This soft= No limit for our liar politicians for example,or religious,etc...

That will not help to stop wars or conflicts.

 

Last edited: Nov 4, 2016

That's the point, the more chaos the better..... Let the money flow....... ;)

 

Hate to break it to you, but this stuff is already in the arsenal of the intelligence in several countries. Commercial software like this is just really cool and would make people more knowledgeable and aware, which is a good thing. You need a large sample from a person spoken in a certain way to be able to use it to add to someone's speech. There are also ways to differentiate real speech from synthetically engineered in this way. No need to be scared of this any more than Photoshop.

 

I heard some Google DAW is on the way too... Might be even more relevant than this, hue hue

 

This is similar of the IRCAM project : http://recherche.ircam.fr/anasyn/obin/pmwiki/pmwiki.php/Main/Creation
They use old records from died people and recreate a speech. It's amazing.

 

Something like this must be Forbidden, I doubt that things like change.org may help. As a producer, this can be pretty helpful maybe in the first versions it will sound pretty bad but in the 3rd or 4th version it may sound more real. A lot of cases have been in Mexico (and I'm pretty sure all around the world also) when a politician is involucrate in a corruption case when a phone call or whatever audio material is involved, the politician says that that is not him/her voice, etc.

 

Is a nightmare