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

Lyrebird – An API to copy the voice of anyone

lyrebird.ai

Post reply on HN
Print view View original

221–230 of 311 posts

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

#221

Post by Negative1 »

Ensorceled wrote: post #165
k2xl wrote: post #163

Earlier quoted context omitted.

I was just thinking that Stephen Hawking would perhaps be interested in using this to replace his current voice synthesizer (feeding in old interviews of him when he could talk). He has said that he has adopted the current voice since he has associated it with his own, but I wonder if he would prefer his old actual voice.

I think Hawking is now so firmly tied to that voice that he would probably never switch for public speaking engagements and the like. I could see him doing such a switch for personal interactions.

I recall his biggest qualm with his current synthesized voice is that it did not come with a British accent. :-)

I'm not sure how sentimental he is but he does seem quite tied to that voice since there have been lots of advancements in voice synthesis since he originally got this and yet he's chosen to keep this one.

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

#222

Post by tommoor »

pbhjpbhj wrote: post #126

Last week on BBC Radio 4 I heard of a woman who was losing her voice through disease (MND maybe?), a similar system was being anticipated and she was saving voice samples to seed it with. She had been a singer and strongly identified her self with her voice, she wanted to be able to use a speech synthesis system that had her own voice pattern. Apologies if this was already mentioned, but it seems to be a use others h…

Actually fantastic to see there are legitimate uses for this tech beyond the obvious

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

#223

Post by uremog »

bpicolo wrote: post #115
Infernal wrote: post #114

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

And then the generators train their own generation NN against that :P

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

#224

Post by Infernal »

i336_ wrote: post #147
microtherion wrote: post #141

Earlier quoted context omitted.

I haven't worked extensively in voice adaptation, but I learned working in text-to-speech that adding a bit of reverb is quite effective at covering up artifacts. Something similar seems to be going on in live vocals. If you lack confidence in your own voice, adding a bit of reverb can make it sound much better. Not sure what's going on — whether the reverb jams the critical listening facilities in one's brain or som…

Wow. TIL x 2! Now I understand why I liked adding a bit of reverb when listening to old MOD/IT/S3M audio files - it covered up the "digitalness" of the song structure a bit. Thanks for the live vocals tidbit too, that's definitely something to file away. I wonder how far you could push that in a presentational context (ie, when giving speeches), or whether "who left the speakers in 'dramatic cathedral' mode" would ha…

In my (admittedly limited) experience mixing for both recording and live settings, I can say that the "sounds great" comes a long way before the "dramatic cathedral mode". If you can listen to it and hear reverb (unless you're going for that effect) you're doing it wrong. What you want is a bit of fullness, slightly softer edges at the end of words/sentences.

It's similar to the difference between 24fps cinema and 60fps home video. The video/clean signal retains more of the original information and is "more correct", but 24fps/touch of reverb adds a nuance that keeps things from getting too clinical. As to why we interpret clean signal == clinical == bad.... I can't really speculate.

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

#225

Post by swamp40 »

keithwhor wrote: post #214

I love this. The business model is too good to be true. 1. Open source voice-copying software 2. At worst, create entire market of voice-fraudsters, at best, very few voice-fraudsters but very high and very real perception of fear of such 3. Become leading security experts in voice fraud detection 4. Sell software / time / services to intelligence agencies, governments, law enforcement, news networks Ethically I'm a…

You could charge 99 cents to have Siri talk in your favorite actor's voice.

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

#226

Post by hoschicz »

uremog wrote: post #223
bpicolo wrote: post #115

Earlier quoted context omitted.

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

And then the generators train their own generation NN against that :P

And you have invented Generative Adversarial Networks. They are the basis of all new ML findings, like pix2pix.

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

#227

Post by twothamendment »

qznc wrote: post #121
qeternity wrote: post #45

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.

It might just be about the quality of the source. It seems they used public speeches. Obama sounds like he stands in a stadium. Trump is closer like a TV debate. Hillary sounds off to me, though.

Hillary sounded very off, but what is new? Joking aside, Obama didn't sound too bad, but the Hillary voice was bad enough I wouldn't have included it in a demo.

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

#229

Post by Frenchgeek »

return0 wrote: post #187
LegendaryPatMan wrote: post #91

This is pretty basic at the moment and it's terrifying. Yeah, it has an MS Sam feel to it, but as the tech improves and we know it will, you could use a service like this to put words in someone's mouth. Think about how you could trip up a CEO or a Politician by playing some random clip that they never said. When that gets into the Zeitgeist judgments will be made in the court of public opinion devoid of facts or rea…

There are human impersonators already. I suppose it's not that easy to fake a visible, high-ranking person for long.

Bad joke of the day: Even Trump can't do it, and he really is President of the U.S.!
Post reply on HN