Live data from Hacker News

Lyrebird – An API to copy the voice of anyone

lyrebird.ai

111–120 of 311 posts

Re: Lyrebird – An API to copy the voice of anyone

#114

While all of these vec2speech type models are impressive, I get the feeling that most of the comments didn't listen to any of the samples. It's still distinctly robotic sounding, probably has quite a bit of garbage output that needs to be filtered manually (as many of these nets often have) and is a far cry from fooling a human.

In the first clip, I'd say 80% of the soundbites were obviously robot-like, but one or two of the "Obama" quotes were startlingly clear - "The good news is, that they will offer the technology to anyone" - I can't hear anything wrong with that in the first clip at all. If they were all that quality I'd say we'd be easily fooled. As a proof of concept this is pretty big.

Re: Lyrebird – An API to copy the voice of anyone

#115

While all of these vec2speech type models are impressive, I get the feeling that most of the comments didn't listen to any of the samples. It's still distinctly robotic sounding, probably has quite a bit of garbage output that needs to be filtered manually (as many of these nets often have) and is a far cry from fooling a human.

In the first clip, I'd say 80% of the soundbites were obviously robot-like, but one or two of the "Obama" quotes were startlingly clear - "The good news is, that they will offer the technology to anyone" - I can't hear anything wrong with that in the first clip at all. If they were all that quality I'd say we'd be easily fooled. As a proof of concept this is pretty big.

I can definitely hear issues with that phrase. It has quite robotic drop-offs.

Though coming soon: Neural networks to determine whether speech is NN-generated? :P

Re: Lyrebird – An API to copy the voice of anyone

#116
post #80

Earlier quoted context omitted.

Forget dead husbands, with this tech, it will be hard to trust anything a politician said. Basically, once they master adding this to video, ANYTHING could be construed against anyone. Want a video of a politician saying "Hitler was right" to cheering masses? Want a video about a president saying it's time to start Nuclear War One? You can make that.

"Forget dead husbands, with this tech, it will be hard to trust anything a politician said." Like we can trust anything a politician says/has said today anyway!

I meant it as you can't trust recording of what someone said. Basically any audio could be faked.

Which would be great for people like Trump. "Trust me, that audio is fake news. Fake!"

Re: Lyrebird – An API to copy the voice of anyone

#117

Earlier quoted context omitted.

In the first clip, I'd say 80% of the soundbites were obviously robot-like, but one or two of the "Obama" quotes were startlingly clear - "The good news is, that they will offer the technology to anyone" - I can't hear anything wrong with that in the first clip at all. If they were all that quality I'd say we'd be easily fooled. As a proof of concept this is pretty big.

I can definitely hear issues with that phrase. It has quite robotic drop-offs. Though coming soon: Neural networks to determine whether speech is NN-generated? :P

> Neural networks to determine whether speech is NN-generated?

I guess this would be an ideal use case for a generative adversarial network based approach.

Re: Lyrebird – An API to copy the voice of anyone

#118
post #20
post #19

It's there any copyright protections for a person's voice? If not, David Attenborough and Morgan Freeman will be lead voice actors in my next game project

AFAIK not copyright per se in the traditional sense, but there is a "likeness right".

Tom Waits sued for this reason multiple times [1].

I guess he had a strong case because in all three cases he was (or so he claimed) approached to do a commercial and the advertisers went with a Waits-like surrogate after he declined.

https://en.wikipedia.org/wiki/Tom_Waits#Lawsuits

Post reply on HN