Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI Clones Your Voice After Listening for 5 Seconds (2018)

google.github.io

Post reply on HN
Print view View original

71–80 of 338 posts

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#71

Post by hurrdurr2 »

carapace wrote: post #46
goodmachine wrote: post #7

The malign applications of this technology greatly outweigh the benign. Discuss.

Yes, I think there are almost no legitimate uses for the Farnsworth Device. https://theinfosphere.org/A_Device_That_Makes_Anyone_Sound_L... My personal hell: My mother has dementia and a land line telephone. Scammers call all the time. All day long. (Although the last few days have been pretty good, I assume somebody somewhere is doing their jobs. The scammers will adapt.) One thing they do is spoof their number to h…

Back when I worked as a telemarketer in high school a long time ago, we sold paper subscriptions, and usually the people that didn't cuss us out and hang up right away are the lonely old people who just wanted to chat. I lasted two months and had to quit; felt like we were just taking advantage of them.

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#73

Post by BOBOTWINSTON »

pcmaffey wrote: post #37
Lordarminius wrote: post #12

AI can make decisions, create deep fakes, and now, clone voices. It may be that the next big business opportunity lies in creating 'anti-AI' technology just as it did with antiviruses in the 90's and 2000's

AI that detects AI seems entirely plausible. And like all “anti” measures, is another arms race (and if I put my scifi hat on, is what may lead to AI self-awareness).

Sort of reminds me of a talk Valve gave about creating an anti-cheat for Counter-Strike using AI. When asked if they were worried about people using AI to create cheats to fool the AI, his answer was essentially that it was an arms-race won by the person with more data/processing power. That person would most likely always be Valve.

Link to talk: https://www.youtube.com/watch?v=ObhK8lUfIlc

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#76

Post by lukeplato »

grawprog wrote: post #51

So....I'm going to paste the abstract here because the headline is incredibly misleading and should be changed. >Abstract: We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained…

I took the headline from this Two Minute Papers video: https://www.youtube.com/watch?v=0sR1rU3gLzQ

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#77

Post by gist »

Will point out that it is cloning after a short sample and with an unknown speaker. So this is great for that type of comparison and in particular when the person listening does not know much or have great experience with the person speaking.

Now if you were to take something by a well known person (where there is a great deal of audio) it would be much harder to clone anything other than a really short passage.

This would be similar to faking handwriting. Easier to fake one word than to fake three pages. Easier to fake something where you have little to compare a pattern (less can go wrong).

Not saying this isn't impressive it is. But it's also a bit of a trick based on the very short clips (both samples and created).

I would say that a trained person could do a better fake because they could take into account all the info and be less likely to make a mistake.

Now sure you could manually change the AI as well doing the same thing.

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#78

Post by Scarblac »

pcmaffey wrote: post #37
Lordarminius wrote: post #12

AI can make decisions, create deep fakes, and now, clone voices. It may be that the next big business opportunity lies in creating 'anti-AI' technology just as it did with antiviruses in the 90's and 2000's

AI that detects AI seems entirely plausible. And like all “anti” measures, is another arms race (and if I put my scifi hat on, is what may lead to AI self-awareness).

In Greg Egan's _Permutation City_ this is mentioned in passing (an arms race between AI video call spam bots and AIs screening the calls for spam while impersonating the owner of the phone).

The anti-spam software loses because eventually having self-aware AI view spam calls 24/7 was considered torture and they weren't allowed to go that far.

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#79

Post by TallGuyShort »

hans1729 wrote: post #22
Lordarminius wrote: post #12

AI can make decisions, create deep fakes, and now, clone voices. It may be that the next big business opportunity lies in creating 'anti-AI' technology just as it did with antiviruses in the 90's and 2000's

Good luck with that. The best product you'll come up with is some sort of snake oil. The whole point of GANs is that you can't really "detect" the synthesized components anymore. Not that this would/will stop people from claiming otherwise in the spirit of profitablity :-)

Snake oil-tier anti-ML might do the trick. One of the problems is the level of confidence people put into ML in the first, when a lot of times it's also snake oil-quality. Just being able to cast doubt on that again would help prevent a loss of healthy skepticism and critical thinking.
Post reply on HN