Startup Lyrebird announces API to replicate life-like voices of people using Artificial Intelligence

[Virssagòn]

Only a few days ago, the Montréal-based startup Lyrebird announced in a press release that they would be releasing an API to accurately replicate human voices. While I'm very excited about this new technology, it also scares the shit out of me!

What do you think about the demo's given?

The startup Lyrebird announced in a press release on their website that they would be releasing an API to accurately replicate human voices. The new company is a spinoff founded by researchers of the MILA lab at the University of Montréal.

Features

The new API will be able to accurately reproduce someone's voice by creating a unique voice identifier key from audio fragments. Only 1 minute of audio should already be enough to make the end result quite life-like, which is why this technology is so ground breaking.

The software doesn't only reproduce the voice, but also allows the produced voice to have different kind of pitches and intonations, without losing its resemblance to the original. For those who are curious what the result sounds like, there are plenty of fragments on the demo page of Lyrebird's website, such as a "discussion" between the voices of well-known US politicians about their software suite.

Ethics

Of course, a groundbreaking development like this one carry some concerns with them. Being able to replicate anyone's voice with free software tools allows one to impersonate anyone they have a voice recording of. Especially in court cases, a voice recording will have to be dismissed as evidence, as now it is virtually impossible to make the distinction between a real recording and a fabricated one. The Lyrebird team discusses this topic as well on their website, saying they wish to publicly release the API to make sure everyone has equal access to it, making sure the existence of it is well-known, so that society is alert to its repercussions.

Future visions

The new technology sure brings a lot of exciting new possibilities: replica's of actors' voices in movies, giving life-like voices to AI robots, etc..

However, as with all new technologies, legislation will have to catch up to dictate how society will accept this new change into their daily lives. I, for one, am curious what the future will bring when the Lyrebird API gets actually released to the public, and other companies can adopt the new technology into their services.​

http://www.blackholetec.com/main/ar...e-voices-people-using-artificial-intelligence

https://lyrebird.ai/demo

 

[Agent Smith]

Old news. I read about this at the PaleMoon forum several months ago. What this means is that you no longer can trust a voice over a phone and you shouldn't use voice biometrics.

 

[Virssagòn]

Old news. I read about this at the PaleMoon forum several months ago. What this means is that you no longer can trust a voice over a phone and you shouldn't use voice biometrics.

Great that you heard about it before they lifted the veil 2-3 days ago... Anyway there have been others creating the same kind of technology like Project VoCo, but they required 20 minutes to entirely mimic a voice; in addition to that, Lyrebird is able to mimic and change the voice's emotional state in no more than 60 seconds.

Everything else you say is true and I'm 100% sure you should take that advice. Now, are there any other thoughts from other people?

 

[Darren]

Old news. I read about this at the PaleMoon forum several months ago. What this means is that you no longer can trust a voice over a phone and you shouldn't use voice biometrics.

If you're just going to be an asshole don't comment.

I expected something like this to get developed. The lines between computers and humans is just going to get fuzzier. Think of the changes made to personal voice assistants in the past decade. I can dictate texts full speed to Google Voice and a decade ago you could barely tell your phone to call a specific person without it dialing everyone in your address book except the person you're trying to call.

 

[Agent Smith]

If you're just going to be an asshole don't comment.

I wasn't trying to be an asshole. I read about this very technology waaay before it was posted here. It's old news and on the Internet, old means at least 3 days. LOL! Don't be a myopic troll!

 

[Darren]

You said "several months" and the press release is from 3 days ago. Pick one.

 

[Intel_man]

I wasn't trying to be an asshole.

Well you were being one. You don't have to try to be an asshole to be an asshole.

I read about this very technology waaay before it was posted here.

So how come you didn't forward that news onto this forum when you first read about it?

 

[Virssagòn]

If you're just going to be an asshole don't comment.

I expected something like this to get developed. The lines between computers and humans is just going to get fuzzier. Think of the changes made to personal voice assistants in the past decade. I can dictate texts full speed to Google Voice and a decade ago you could barely tell your phone to call a specific person without it dialing everyone in your address book except the person you're trying to call.

That's a new perspective I didn't think about yet, but this seems to be a different kind of of technology as it simply studies a voice it can mimic; maybe word recognition is also used, but the technology is also used to speak words they didn't actually said in those 60 seconds.

 

[Agent Smith]

So how come you didn't forward that news onto this forum when you first read about it?

Because I don't care about this forum and its "asshole" audience? LOL!

 

[Intel_man]

and its "asshole" audience?

Why? Because people have views that doesn't align with yours?

Grow up.