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

AI speech generator 'reaches human parity' – but it's too dangerous to release

livescience.com

Post reply on HN
Print view View original

11–20 of 68 posts

Re: AI speech generator 'reaches human parity' – but it's too dangerous to release

#11

Post by digitalsushi »

weakest link, if they dont release this, someone else will release one. every time someone noble invents another gen ai toy/weapon, they lock it down with post filters so it cant be used for evil, and then a second person forks it, pops the safeties off, and tells the world to go nuts.

social solutions take too long to use against the tech, but tech solutions are fallible. to be defeatist about it, there's going to be a golden window of time here where some really nasty scams have no impedance.

Re: AI speech generator 'reaches human parity' – but it's too dangerous to release

#12

Post by Paul-Craft »

jd115 wrote: post #2

I'm old enough to remember some number of months ago when GPT2 was described as "too dangerous to release".

Huh. Today, a college kid without even any underlying knowledge of the math can train their own GPT-2-level language model as a semester project.

Re: AI speech generator 'reaches human parity' – but it's too dangerous to release

#13

Post by michaelbuckbee »

pphysch wrote: post #4

Speech generation has gotten really good, but there's simply no way to faithfully recreate someone's vocal idiosyncracies and cadence with just "a few seconds" of real audio. That's where the models tend to fall short.

This was my thought as well, but someone pointed out to me that regional accent identification captures a large percentage of cadence and inflection differences (specific word choices and turns of phrase obviously would still not be there).

Re: AI speech generator 'reaches human parity' – but it's too dangerous to release

#14

Post by klowner »

01HNNWZ0MV43FF wrote: post #7
jd115 wrote: post #2

I'm old enough to remember some number of months ago when GPT2 was described as "too dangerous to release".

Remember when the PlayStation 2 was "technically a supercomputer" and taking LSD a certain number of times made you insane? Great moments in marketing history

Oh yeah I vaguely recall news reports about how the PS2 was so powerful it could be used for missile guidance or some nonsense?

Re: AI speech generator 'reaches human parity' – but it's too dangerous to release

#19

Post by carapace »

https://arxiv.org/abs/2406.05370

> Our experiments on the LibriSpeech and VCTK datasets show that VALL-E 2 surpasses previous systems in speech robustness, naturalness, and speaker similarity. It is the first of its kind to reach human parity on these benchmarks. Moreover, VALL-E 2 consistently synthesizes high-quality speech, even for sentences that are traditionally challenging due to their complexity or repetitive phrases

https://www.microsoft.com/en-us/research/project/vall-e-x/va...

> This page is for research demonstration purposes only. Currently, we have no plans to incorporate VALL-E 2 into a product or expand access to the public.

If you go back and look at older cities they almost all have the same pattern: walls and gates.

I figure now that the Internet is a badlands roamed by robots pretending to be people as they attempt to rob you for their masters, we'll see the formation of cryptologically-secured enclaves. Maybe? Who knows?

At this point I'm pretty much going to restrict online communication to encrypted authenticated channels. (Heck, I should sign this comment, eh? If only as a performance?) Hopefully it remains difficult to build an AI that can guess large numbers. ;P

Re: AI speech generator 'reaches human parity' – but it's too dangerous to release

#20

Post by Melomololotolo »

pphysch wrote: post #4

Speech generation has gotten really good, but there's simply no way to faithfully recreate someone's vocal idiosyncracies and cadence with just "a few seconds" of real audio. That's where the models tend to fall short.

I don't think it's hard to get more than a few seconds of voice from many people.

'hi, sry to call you I'm Cindy and I'm from your insurance. I'm calling regarding your car crash ...'.

Post reply on HN