StreamVC: Real-Time Low-Latency Voice Conversion • Hacker News Board

Re: StreamVC: Real-Time Low-Latency Voice Conversion

#41

Post by neilk » Fri, Jul 12, 2024, 9:55 PM UTC

webappguy wrote: post #26

neilk wrote: post #22

What are the anticipated use cases? I know of one: transgender people often would like to alter the timbre of their voice and spend a lot of time training their voice. At least for online scenarios, this can just do it. But other than that AI voice altering research seems like it benefits mostly scammers? I’m just wondering what they tell themselves they’re doing. I didn’t see this in the paper.

RFK Jr.

You’re getting downvoted perhaps because people think you’re saying something political, but I think you mean “a stronger voice for people with physical issues producing speech”.

I have a friend who has a faint, scratchy voice because his throat is riddled with benign growths that a surgeon has to dig out of him every few years. Eventually he will probably lose his voice. Maybe?

Re: StreamVC: Real-Time Low-Latency Voice Conversion

#42

Post by ganeshkrishnan » Fri, Jul 12, 2024, 10:34 PM UTC

manishsharan wrote: post #24

Are there any use cases that is driving this ? Is there a huge burning need for technology ? Are kidnappers and con-men a huge under-served market that Google is hoping to serve ? Deep Fake videos not convincing enough to serve the need of fraudsters ? I am totally against regulating AI but shit like this gives fodder to the other side.

I had couple of usecases for this. One was one of my very young cousin usually has voice chat in his gaming sessions and I wanted to anonymize it.

The second was we got a very enthusiastic video spokesperson but unfortunately she has a very thick non-american accent and this can help us alleviate it.

Re: StreamVC: Real-Time Low-Latency Voice Conversion

#43

Post by viila » Sat, Jul 13, 2024, 1:43 PM UTC

neilk wrote: post #22

What are the anticipated use cases? I know of one: transgender people often would like to alter the timbre of their voice and spend a lot of time training their voice. At least for online scenarios, this can just do it. But other than that AI voice altering research seems like it benefits mostly scammers? I’m just wondering what they tell themselves they’re doing. I didn’t see this in the paper.

The first case you mention are scammers too really. They're trying to deceive others into believing they're something they're not, especially with this sort of voice manipulation.

Re: StreamVC: Real-Time Low-Latency Voice Conversion

#44

Post by sahmeepee » Sun, Jul 14, 2024, 9:32 AM UTC

ganeshkrishnan wrote: post #42

manishsharan wrote: post #24

Are there any use cases that is driving this ? Is there a huge burning need for technology ? Are kidnappers and con-men a huge under-served market that Google is hoping to serve ? Deep Fake videos not convincing enough to serve the need of fraudsters ? I am totally against regulating AI but shit like this gives fodder to the other side.

I had couple of usecases for this. One was one of my very young cousin usually has voice chat in his gaming sessions and I wanted to anonymize it. The second was we got a very enthusiastic video spokesperson but unfortunately she has a very thick non-american accent and this can help us alleviate it.

This will not resolve your second issue as it replaces timbre but not accent.