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

241–250 of 338 posts

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

#241

Post by drdec »

losteric wrote: post #220
inetknght wrote: post #214

Earlier quoted context omitted.

I live in Houston. I recently read a Houston Chronicle article describing very similar scenario. I don't have the exact link (it was from 2019), but here's one from 2013 [0]. Combined with the inability to verify the actual phone number displayed on caller ID has led me to tell all of my family to not ever accept a phone call from a number they don't recognize. There's literally zero trust in our phone system upon wh…

Given caller ID spoofing, they really shouldn't even accept calls from numbers they do recognize... especially with tech like this. Let it go to voice mail then return the call afterwards.

So what's the end game there - using voicemail as a poor man's texting?

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

#242

Post by airstrike »

drbawb wrote: post #96
AbbasHaiderAli wrote: post #39

Wow, impressive results! Already a few examples in the comments of what bad actors could do this tech. I wanted to share an example of something good. I lost my dad about 6 years ago after a Stage 4 cancer diagnosis and a 3 month rapid diagnosis. I have some, but not a lot of video content of him from over the years. My mom still misses him terribly so for her 60th birthday I tried to splice together an audio message…

When I was doing a computer repair: I remember a woman coming in with a digital answering machine; the kind that stored its recordings in volatile flash. During a thunderstorm the night prior the machine lost power, and subsequently lost all the stored recordings. As it happens some of those lost recordings included messages from the woman's late mother. That moment has stuck with me for many, many years. The heartbr…

My pet project I will likely never have the resources to work on would be AI-generated 3D virtual environments based on old photos / videos that you could navigate in VR and relive long lost memories

I'd pay a good amount of money to be able to relive certain experiences from my childhood with that level of immersion

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

#243

Post by JaRail »

moyix wrote: post #92

This is from 2018 – does anyone know if there are pretrained models and code for this? I found https://github.com/CorentinJ/Real-Time-Voice-Cloning , but the generated audio quality was much worse than the samples here.

The biggest missing piece is WaveNet, which is Google's proprietary voice-synthesizer. With only the models trained for this paper, the best you could build is a voice-recognizer. As far as I know, Google only allows people to do TTS with one of their provided voices.

I don't expect them to open it up until other companies/academics have achieved similar results. It's too much of a competitive advantage right now. Alexa, Siri, etc all sound like robots compared to WaveNet (google assistant).

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

#244

Post by jonplackett »

lukeplato wrote: post #172
jonplackett wrote: post #25

Do papers like this have code to play with anywhere?

from two minute papers video description: > An unofficial implementation of this paper is available here. Note that this was not made by the authors of the original paper and may contain deviations from the described technique - please judge its results accordingly! https://github.com/CorentinJ/Real-Time-Voice-Cloning

Funny, it gives them all a slight American accent!

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

#245

Post by justinjlynn »

sangnoir wrote: post #81
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

Is it that difficult to create/retrofit an AV container format for cryptographically signed audio and video streams? Key management & revocation could be a pain, but it's something that consumer electronics companies like Apple could do: think of it as the MPEG LA, but with signature checking & non-repudiation.

Congratulations, you have now created a class of people who can forge audio and video streams at will, relatively cheaply - and an underclass of people who cannot and may not even be able to record genuine footage they wish to record. This is not a road you want to go down.

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

#246

Post by danShumway »

Dramatize wrote: post #202
danShumway wrote: post #93

Earlier quoted context omitted.

I'm currently working by myself on a game that will likely launch without voice acting (text only) because I don't have the money or skill to find and pay voice actors. If I could act out the dialog myself and then purchase or generate voices other than my own to overlay on top of those performances, the quality and accessibility of my finished product would go up dramatically. That would also open up the door for mo…

Have you tried out Replica? I can hook you up with a beta account to see if it'll help with your voice acting. https://replicastudios.com/

This looks really interesting!

That being said, because mod support is such a huge part of the design of this specific game, I have a policy that I won't use any tools or libraries that aren't either owned by me, that are Open Source, or that are exporting to common, open formats that can be freely read, manipulated and written by Open Source programs.

If I used a licensed product to generate my voices, I would be in the same position as if I hired a voice actor -- I wouldn't have a tool that I was free to ship with the game that any modder could use to edit or add dialog, or to even create new characters with new voices.

The few exceptions for proprietary tools I'm willing to tolerate for this specific game are things that generate MIDI output, sounds, fonts, and PNG files. Everything else is either Open Source or completely owned by me. Even for the final assets like mp3 files and fonts, nothing can be licensed, because I want to have full control over when players have the ability to remix and distribute game assets in their mods. I need to know that 20 years from now players will still have access to everything in the game.

I don't want to derail, so to bring that back around to the current discussion on AI-generated fakes, I believe these kinds of AI techniques should be freely available. A world where AI-fakes are considered so dangerous that only a few select guardians can control them is a world where, to me, this technology stops being useful. I'm not saying Replica is in that position -- I'm just speaking to a broad trend in the conversation around AI.

I think we'll start to see more calls to have single companies controlling AI under the guise of being able to ban bad actors or prevent abuse. I think that would be a mistake -- if anything, ubiquitous technology makes it easier for society to adapt to that technology. A purely SaaS, licensed model for AI generated faces, voices, and text would be all of the negatives of this technology with none of the positives that come from Open access and creative usage.

Gatekeeping won't work, we just have to adapt.

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

#247

Post by r00fus »

thedaemon wrote: post #231
r00fus wrote: post #195

Earlier quoted context omitted.

POTS just needs to die unless they allow for authenticated CID. One could wonder if this was some sort of conspiracy to break one of the most successful protocols in the world (or at least not update it so it dies by neglect) to increase profits by other means.

POTS is pretty much dead almost everywhere in the USA, most are VOiP these days. They are not replacing the copper wire.

Isn't that a bit pedantic? Perhaps Im conflating PTSN and POTS. The fact that you have publicly addressable phone number is the important part.

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

#248

Post by bjelkeman-again »

r00fus wrote: post #193
robbiemitchell wrote: post #183

Earlier quoted context omitted.

I told my wife that if I ever mention while on a phone call, she should know that I am in trouble an unable to speak freely. Sound like we'll all need more things like this eventually :(

While it's a great idea, how do you test this? Is it worth the time? All my loved ones are on my iCloud so I would just ping their phone/watch while confirming location and asking the assailant to let you hear the phone ping on the line.

Find My Friend is so unreliable for me it is nearly worthless. Apple isn’t really delivering what I need.

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

#250

Post by LargoLasskhyfv »

inetknght wrote: post #226
losteric wrote: post #220

Earlier quoted context omitted.

Given caller ID spoofing, they really shouldn't even accept calls from numbers they do recognize... especially with tech like this. Let it go to voice mail then return the call afterwards.

I wholeheartedly agree. I don't answer the phone for unknown numbers unless I'm expecting a call from an unknown number; the expectation will have been set up via prior correspondence. Unfortunately, not everyone can do that. Some people are legally required to answer the phone, even if they don't recognize the number. And unfortunately many businesses only communicate via the phone system. So, unfortunately, our ent…

Why are there people who are legally required to answer the phone? On what grounds? Why? (Assuming private persons here)
Post reply on HN