Adobe Is Working On 'Photoshop For Audio' That Will Let You Add Words Someone Never Said (theverge.com)
An anonymous reader quotes a report from The Verge: 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. 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. 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. "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."
I look forward to Donald Trump claiming he was its first victim on that bus.
The article is relatively positive, but among other uses, there are 20+ minute audio clips available of pretty much every major politician.
This won't be abused at all.
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...
When recording suspects, police would often like change or insert a word or a few words in order to manufacture evidence by changing part of the narrative.
FTFY
OTOH, if it's really good enough to be undetectable, it might cause a lot of legitimate and unaltered recordings to be thrown out of court on the grounds of reasonable doubt.
'The Economy' is a giant Ponzi scheme whose most pitiable suckers are the youngest among us and the yet-unborn.
Isn't that Adobe Audition?
Wanna buy a shirt?
https://www.redbubble.com/people/stealthfinger/shop?asc=u
Richard and Sal's lives just got easier.
-linux... they can't *give* that shit away.
...just in time for the next US Presidential Election cycle.
No. That was goldwave. Shareware from the '90s.
I have perfect name for this future product - Adobe Trump. This way when you use it to make people say awful things you are trumping them.
See subject
file this one under "things no one is asking for"
It could be used by or against law enforcement agencies to alter witness statements or the confession of a suspect.
It could be used to ruin politicians or any public figure.
It could also put voice actors out of work. Why pay the talent when all you need is 20 minutes of their voice and now you can add audio to an entire movie.
This is nothing new under the sun. Entire public transportation system messaging in Pilsen is synthetized from small voice corpus narrated by woman who did narrated each station one by one formerly. There are two departments at univerzity of West bohemia with hard to distinguish from real speech result. The adobe's 20 minutes minimum is definitely just a safety duration so there is chance that necessary speech bits appears.
Yeah. Now all those photosnarks that have a picture of a politician saying something they didn't say will have audio clips attached.
We really are moving to a truth-free society.
http://www.geoffreylandis.com
must already have a patent on this.
I am pretty sure it was posted on Slashdot (can't find it), but the Boston Globe reported in 2002 that scientists at MIT could convincingly alter video to make it appear that someone said something they didn't, with only 2 minutes of footage:
http://www.rense.com/general25...
(Link to article on Boston Globe is dead.) They couldn't alter the audio convincingly, or at least didn't try. However, I also recall seeing on Slashdot (10+ years ago; also can't find it) that someone (Bell? MIT?) could take about 2,000 recorded words from an individual and create convincing audio of words and sentences not previously recorded.
Post-truth politics won't matter when someone releases convincingly altered video and audio of a public figure doing something that they never did.
In the end... Only the lawyers will win.
Perfect for CNN.
Nope, CBS. "Fake but accurate" is their standard for "news" they make up.
Even more perfect for Fox.
I must have missed the part of this tech which only allows it to be abused by Democrats. Pretty neat, but how well does it detect a change in Party Affiliation? And what about non affiliated parties?
I think NBC will be making use of this to accompany their film edits.
When Fascism comes to America, it will call itself Anti-Fascism, and tell you to give up your guns.
I did this sort of thing for a class project with Audacity. The person I was working with constantly flubbed their lines, so I had to stitch their lines together using things they didn't screw up until I had completed lines. It's really not hard, this just automates the process.
Others have called out how this will impact politicians and law enforcement. On a slightly different note, how many voice actors have recorded twenty minutes of dialog in the past? How many of their contracts give them control over how the movie studios use those recordings or mandate that the studios give them royalties for using "remixed" versions of their voices?
For example why pay (a bunch of money to) Mark Hamill to provide the voice for a new animated version of the Joker when you can use this tool to put Hamill's words in Joker's mouth by paying (a lot less) money to Adobe?
And if the tool becomes good enough, why not "find" a "lost" Freddie Mercury (or $YOUR_FAVORITE_ARTIST) recording that he never sang? It may sound exactly like Mercury, but the recording industry will argue that it's different enough that they don't owe Mercury's estate (or $YOUR_FAVORITE_ARTIST) anything.
Currently, politicians and the powerful elites are rarely heard from in person, anyway. We get to see the results of their secret meetings and closed-door sessions through carefully crafted press releases and the societal changes we see every day. The controllers, I'm sure, positively love this technology, because it will give them an additional outlet to turn the screws on the little guys.
Think about it, ubiquitous mobile video was probably the last tool that was still on the side of the people. Now, when a powerful elite gets caught talking about how he feels about minorities or wants to bring groups of people "to heel", they can just say the video was compromised. And when one of us proles becomes too uppity and starts criticizing them, they can easily edit us into being a racist or sexist or whatever -ist they come up with this week to suit their "two minutes hate".
Like Photoshop, Project VoCo is designed to be a state-of-the-art audio editing application.
It's in TFA, so I guess /. isn't to blame. Nice job, Verge editor.
Our entire historical "record" is suspect, not even audio can be believed anymore....
How long before some political pundit, campaign or right/left wing fanatic starts outputting doctored "recordings" with this kind of software to try to discredit their rivals? This election season has seen enough off the wall conspiracy theories (Trump sniffing cocaine, Hillary having a terminal illness, plots to sabotage microphones, etc) with little to no evidence backing them let alone the firestorm will happen there are videos (even badly done ones) "proving" either sides point.
"...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."
Enough with this "innocent" sales bullshit. I am far more concerned about how this tool can and will be used against me, in a court of law, forcing me to hire enough expertise to defend against shit I never said.
The average citizen can't even remotely afford a good legal defense these days. This is going to make that even more difficult by having to hire appropriate audio experts to analyze audio recordings to determine if they've been manipulated or not.
And no, this isn't like Photoshop, where often the only tool that is necessary to validate manipulation is the human eye and common sense (yeah, I'm talking to you magazine editors, who still feel the need to digitally alter some of the most naturally beautiful humans on the planet.)
voice authentication systems to be bypassed with ease now.
How long before we get Adobe DNA editor where DNA sequences from blood found at the crime scene can be edited to match the DNA of the suspect?
**Life is too short to be serious**
Are you going to cry when orange paedo hitler loses?
I can tell from some of the harmonics and from hearing quite a few shops in my time.
Your statement seems a little lopsided since most of the lies/conspiracy theories (at least in the presidential campaign) have been coming out of the Republican sphere (Hillary has a terminal illness, the press is plotting against us, Obama is a secret Muslim, etc). If such software becomes commonplace BOTH sides will abuse it, and any abusers on either side deserve SEVERE penalties when they do so.
Is Fox News already using this, or is Sean Hannity really that stupid?
Can it add subliminal suggestive messages too? Of course, I'm being facetious but when, not if, this technology is misused, wouldn't it be a good idea to embed subliminal audio watermarking so that juries and the media will know that the audio is faked?
The audio from Neil Armstrong can finally be corrected.
Because it's so terribly difficult to tamper with perception and memory.
Oblig: My voice is my passport.
Any single factor authentication scheme is just begging to be bypassed...
My eyes reflect the stars and a smile lights up my face.
My voice is my passport. Verify me.
> Project VoCo can also apparently generate new words using a speaker's recorded voice
In the Godfather saga, mafia top dog Don Vito di Corleone refused to ever speak on the phone, for fear of the FBI recording his words and editing the tapes into fake conversations. His wisdom retro-actively justifies the high position he achieved in the Cosa Nostra.
In other news:
> 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
The same has been available for singing synthesis since about 2007, but requires several hours (for japanese or spanish) to several weeks' worth of recorded recitals (for english, since that language is not orthographic). The technology is known commercially as Cevio Alys or Yamaha Vocaloid. A very primitive home use imitation also exists called UTau and it's free but has miserable sound quality.
at bell my voice is my password
Another tool Progressives can use to revise history.
What if this technology is already available and being used in combination with man-in-the-middle attacks for the modification of communications in real time? A state-sponsored malicious actor can even start wars between unsuspected countries. Governments don't need to wait for Adobe to write software for their cyberwar arsenals.
The only way to (try and) guard against this that I can think of is cryptographically signing and verifying all important communications, whether between country leaders or between corporations. Maybe this is necessary for personal communications too.
my voice is my passport verify me.
So you say you have this technology that creates words that people never actually said.
But it sounds just like their voice.
Clearly this is how Skynet begins!
Sarah: "No, I can't tell you where I am mom. I was told not to say."
Mom: "Oh, but honey, I need to know where I can reach you. You tell me to hide out here in the cabin like some kind of fugitive and you won't tell me what's going on? I am worried sick dear."
Sarah: "Ok. Here's the number...."
Mom: "Ok. Go ahead.... Uh-huh. I've got it."
Sarah: "I love you mom."
Mom: "I love you too sweetheart."
And, this is just early days. Real terminators don't need to hear twenty minutes worth of a voice to duplicate it. Do you really think he sat down and spoke to Sarah's mom for twenty minutes?
If this happens...audio recordings should no longer be considered as valid or legal evidence. Now someone can actually not have said something but have a recording of them "saying it".
Of course, should Trump win...there will be no fair trial and just a police state of Judge Dredd's running around killing people for breathing wrong.
...and I notice she was sitting on her SWEET CAN I GRAB HER SWEET CAN
voice authentication systems to be bypassed with ease now.
As a great man once said, "There's nothing more useless than a lock with a voice print."
Hopefully this will mean we'll see more John Wayne movies...
-Bob-
Lol, no way will this ever be abused or used for nefarious purposes. *cough*
It's getting to the point where no amount of "evidence" will be able to "prove" or "disprove" anything.
I have incontrovertible photos, video, and audio that show you killed Bob Smith, and you have incontrovertible photos, video, and audio that show you didn't. As for 3rd party witnesses, maybe their audio/video data was hacked and modified, and maybe it wasn't. Who can say?
Just cruising through this digital world at 33 1/3 rpm...
https://www.youtube.com/watch?v=GuZGK7QolaE
My UID is prime!
How is this useful?
Never give up, never surrender.
Today slashdot, tomorrow the world!
http://www.geoffreylandis.com
And similar to how Creative Cloud has made vassals out of people who work on photographs, videos, websites, and presentations, Project VoCo will do the same to people who work with audio.
https://www.youtube.com/watch?...
This already exists. It is called Audacity.
A giant leap backwards for forensics
“He’s not deformed, he’s just drunk!”
Clinton News Network or was it Cia News Network, would really really love this. ...
All the sweet "news" to "make"! And if something is not true, so what, people will see it everywhere for 4 days, and will not see the short and only once broadcasted "news network apology" part some weeks afterwards
Releasing software allowing the editing of spoken words in audio recordings is probably the best way to ensure people know this capability exists. Everyone knows about Photoshop and the kinds of things it makes possible so that the old phrase "the camera never lies" is known to be obsolete. If audio speech editing capabilities were somehow kept from the public the potential for abuse would be much greater.