Slashdot Mirror
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."
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
Difference being that so far doing such tampering requires more complex equipment used by big organisations, thus when a recording appears to be genuine it's hard to claim it's been tampered with. After such tool becomes popular, anything can be suspected to be tampered with.
Slashdot, fix the reply notifications... You won't get away with it...
...just in time for the next US Presidential Election cycle.
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
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
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.
Come on, -1? Really? This is the best comment in the thread. Bababooey to y'all.
I feel sorry for people that don't drink, because when they get up in the morning, that's as good as they're gonna feel
Sadly, this means likely even more revisionist history coming our way.
This is a tool they NEVER thought of in 1984....no need for double speak and re-writing the books, just change what people say....
Light travels faster than sound. This is why some people appear bright until you hear them speak.........
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.
It's fine for Trump though. You'll always be able to spot the fake Trump stuff because in those, he'll use a complete sentence and finish the sentence without blurting out something about ISIS or getting distracted by how angry he is at Rosie O'Donnell in the middle of it.
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....
"...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.)
"file this one under "things no one with a CONSCIENCE is asking for"
There, fixed that for you. There are definitely people looking/hoping for this kind of software, they simply are the useless husks of human garbage who think that lies, deceit & misdirection are perfectly viable means to achieving ones goals. There may be a few legitimate uses, but they are few, far between & easily solved by other actions. If this software is going to enter the commercial sphere there needs to be safeguards, in the form of SEVERE penalties for its misuse and hopefully simple ways to determine if it was used (encoding some kind of audio watermark perhaps?)
Yes, what a service indeed. Now we finally will have the ability to set people up like in the movie Running Man.
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**
who think that lies, deceit & misdirection are perfectly viable means to achieving ones goals.
You just described the human species.
We can do better, of course, but we don't.
I do not want your cheap brainburning drugs. They are useless for work. And I am a working man today.
I am sure that there will be ways to determine whether or not it is an altered audio clip just like it is possible to identify photoshop pictures. Whether it is imperfections, algorithmically induced patterns, meta data, etc.
As this election campaign has proved (yet again), people will believe what they want to believe. So doctored audio clips are not going to add or subtract anything to that equation.
My eyes reflect the stars and a smile lights up my face.
A world where this exists is a world where every recording of speech is potentially (probably) fake. It would make skepticism pretty much mandatory to function. In that respect, it might actually be a good thing.
I do not want your cheap brainburning drugs. They are useless for work. And I am a working man today.
Maybe once the tech is out, Apple will decide that it's pretty cool, and they can invent it and patent it.
I do not want your cheap brainburning drugs. They are useless for work. And I am a working man today.
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.
Don't ascribe traits predominant in US to the entire human race.
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?
Yep..this will be the politicians BEST friend....at least when they want to claim they didn't say it....
Sadly, this means likely even more revisionist history coming our way.
This is a tool they NEVER thought of in 1984....no need for double speak and re-writing the books, just change what people say....
Have a real-time portable version that people wear around their necks and automatically edits what they say.
No one will ever be offended again!
In the free world the media isn't government run; the government is media run.
Hollywood's asking for it. They'll start making sure their contracts regarding perpetual use of likeness of actors can be used to leave actors out of payroll entirely on the next animated film. Especially low-budget direct to video sequels.
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.
I recently saw a doctored video clip on FB (well, obviously doctored to anyone with a minimal amount of critical thinking) that purported to show Obama at public forum admitting he was born in Kenya; but you could tell that certain key words were pasted in from other speeches, and when those strings of words were said, the camera view suddenly cut to a long shot so you couldn't see his mouth; and yet there were people swearing in the comments that it was proof, "there he is saying it". I don't even like Obama but bullshit is bullshit.
Look back up at my post, now look back down, you're on the Internet. Now look back up. I'm a signature.
both for and against.
“Convictions are more dangerous foes of truth than lies.”
Friedrich Nietzsche
you will have those already wanting to believe screaming vindication, and those who don't want to believe arguing vast russian conspiracies. Maybe there is some truth to this whole living in a simulation theory after all. When a copy cannot be distinguished from real, when does it start becoming real itself?
> 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
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
This sounds shopped.
I can tell from some of the vowels and from hearing quite a few shops in my time.
Copyright (c) 1990 - 2014 Dice. All rights reserved. Use of this comment is subject to certain Terms and Conditions.
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!
He's not.
It only happens when people care about the goal more than the means.
Agent K: A *person* is smart. People are dumb, stupid, panicky animals, and you know it.
This is just another form of re-writing. Does it matter if the person said we were always at war with Eurasia or that it is written?
Instead of re-writing books, it is re-writing video.
Luckily there is a company that is in charge of most video and it has "do no evil" as slogan, so we are safe.
Don't fight for your country, if your country does not fight for you.
If it can make the words sound like someone, then it must be able to get the emotions and emphasis correct. I imagine this would be useful in translating someone's voice into a foreign language with all of the correct inflections, emphasis, and emotional impact. If it could be used in real time, you could talk out loud to someone and they could hear the translated version through their ear buds. It might even sound like the person if they learned the language themselves. Of course, your gestures and facial expressions may be out of synchronization. This might be like a "babel fish" for audio. It might make travel and international communication easier. For instance, the people in call-centers would not need to know the language of the person they are helping.
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.
That's why the book was called 1984 and not 2016.
Peter predicted that you would "deliberately forget" creation 2000 years ago...
https://www.youtube.com/watch?...
I shopped at a shop for photoshop so that I could shop some photos to display at the shop show.
My eyes reflect the stars and a smile lights up my face.
There was a movie version of Stanislaw Lem's Futurological Congress that saw parent's point coming -
The Congress
http://www.imdb.com/title/tt1821641/?ref_=nv_sr_1
Robin Wright's character signs away rights to her likeness and voice and later on finds (after everyone has abandoned real life for a virtual existence) that her voice and likeness has attained cult following status and is used by many people as an avatar.
The book was a bit different (more of a psychedelic fever dream) and more political, but the movie was still very good and thought provoking on some of the similar themes -especially on the use of artificial reality as an escape from a mundane or unpleasant reality....Something which we already seem headed towards....
but it also means that truthiness will become more and more subjective
I'm just sayin'
I doubt that any actor, on their agent's advice, would sign such a contract. It would mean income from one and only one project. IOW, the agent would miss out on future income as well as the actor. Besides, studios depend on the name to promote subsequent projects, so which actors of talent (or at least bankability) are going to sign away future income?
There might be a transition period where the A and B-listers who have sufficient clout will refuse to sign such contracts, so the studios will entice lesser-knowns into it, but then all the actors will realise that they'll never have a career that makes them any money, and they'll refuse to sign, as well.
What am I saying? 98% of actors never have a career that makes them any money. Still, not many would willingly give up a career's worth of income.
Studios *may* get to the point where a character is completely synthetic, i.e. completely digitally generated, but those characters can't walk the red carpet, can't interact with fans, etc, although I suppose they can't get involved in scandals, either - mind you, we have a great capacity to forgive our "stars" all but the most heinous crimes and misbehaviour. Look at Robert Downey jr, Carrie Fisher, and others. Drugs, alcohol, rock bottom, and then, to their credit, a return to popularity.
They sentenced me to twenty years of boredom
Words != understanding, although it should improve things a little. I find it difficult to cope with some accents (e.g. Filipino, Indian/Pakistani), so I prefer to use live chat rather than telephone.
They sentenced me to twenty years of boredom
A giant leap backwards for forensics
“He’s not deformed, he’s just drunk!”
I doubt that any actor, on their agent's advice, would sign such a contract.
Back when they signed it, they only imagined "likeness" to be pictures of their face. Future contracts might be examined more closely, but I was more referring to the ones already signed.
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.
totally ... :) .ulz ... can i quote the hugh on this?
whats the fingerprinting here ? i mean, im not gonna go big brother on yow adobe-ass since the tek is there it will be out, under or above ground anyway.
whats the failsafe ?
i can think of about 50 ways to fuck people over with that unless audio becomes inadmissible in court, which again would fuck others over ?
massive !
i would urge the pigfarm to not go ban on yow-ass cos like the cat here says : the tek is here, its too late for the pebbles to vote, constructive options would be helpful on the other hand, maybe blockchain technology to prevent forging
introduce some chaos
Free speech was meant to be free for all... how can anyone grow up in a nanny state ?