Live data from Hacker News

AI Clones Your Voice After Listening for 5 Seconds (2018)

google.github.io

301–310 of 338 posts

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#301

Earlier quoted context omitted.

I told my wife that if I ever mention while on a phone call, she should know that I am in trouble an unable to speak freely. Sound like we'll all need more things like this eventually :(

how do you pronounce the symbols? i mean, 'redacted' is already a pretty strange thing to say by itself.

is a common way of indicating a placeholder.

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#303

Earlier quoted context omitted.

How do you even prepare for something like that... Do we need to assign identifying keywords to each other when we leave home so we know we are really ourselves? Like a vocal pgp?

I told my wife that if I ever mention while on a phone call, she should know that I am in trouble an unable to speak freely. Sound like we'll all need more things like this eventually :(

I invented two code phrases for pretty much exactly the same reason, but in case I ever met myself from the future.

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#304

I once got a call while I was lecturing some students. It was repeated three times in three minutes - I assumed it was an emergency and stepped out. I was greeted by someone explaining that my father had caused a car accident, and they were calling on his behalf. That someone would need to send over some money for repairs or they’d call the police. Sure. They added that their cousin, the driver, is a parolee now hold…

How do you even prepare for something like that... Do we need to assign identifying keywords to each other when we leave home so we know we are really ourselves? Like a vocal pgp?

> How do you even prepare for something like that.

You don't because it statistically never happens. Just like you don't prepare for a plane crash or a lightning bolt striking you.

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#305

“When you see something that is technically sweet, you go ahead and do it and you argue about what to do about it only after you have had your technical success.” —Oppenheimer

The thing is, these topics have already been discussed by philosophers! Questions of authenticity, human subjectivity, reproducibility etc are not new. But for the average joe and the non-philosophically-inclined techie, the thing has to actually exist before they start really talking about it.

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#306

The malign applications of this technology greatly outweigh the benign. Discuss.

Yes, I think there are almost no legitimate uses for the Farnsworth Device. https://theinfosphere.org/A_Device_That_Makes_Anyone_Sound_L... My personal hell: My mother has dementia and a land line telephone. Scammers call all the time. All day long. (Although the last few days have been pretty good, I assume somebody somewhere is doing their jobs. The scammers will adapt.) One thing they do is spoof their number to h…

Land-line telephones are awful because the majority of people who will pick up the phone during the day on Monday-Friday are old or disabled, i.e. easier to manipulate. I don't think I have received a single legitimate phone call during that time. In fact, legit callers know this and know that if they do call for a good reason, the person at the other end will distrust them.

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#307

Earlier quoted context omitted.

I legitimately think this could be huge for self-published authors. It takes a skilled professional about forty hours of work to produce an audiobook from a novel-length manuscript. Tacotron could do it in minutes.

I don't see that coming soon. The voice is one thing, but the performance goes far, far beyond that. Without understanding the text, you can't get good prosody out of a single sentence, much less developing a character for a whole performance. You'd have to "direct" this on a word-by-word basis: "Put the emphasis here. Speed up 10% here. Decrease vocal intensity 25%". You'd end up producing a whole "score", and it wo…

What about using a tablet to direct the piece by drawing? You can get values for the intensity, speed and volume (up/down) pretty easily and intuitively.

Even better if its linked to the voice generation system in real time, then you can save/redo sentences etc. as you go along.

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#308
post #217

Earlier quoted context omitted.

Only ones that care about the appearance of propriety though, presumably most never had to try to produce convincing fakes when their word was already law?

>Only ones that care about the appearance of propriety though Such as the United States?

USA is a plutocracy. Source - this study:

https://www.cambridge.org/core/journals/perspectives-on-poli...

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#309

Earlier quoted context omitted.

Ubik? Though that is not about artificial personality constructs, it's about communicating with loved ones in half-dead states.

This idea crops up in a few of his novels and stories, but I think it’s most fleshed-out in Ubik, yeah.

Under the hood they are all about religious Gnosticism and the physical universe as a false facade to the "true" universe. VALIS is a pretty good explication as well as a really good book; if you are into mental illness+theology, only then is his Exegesis a good read

Re: AI Clones Your Voice After Listening for 5 Seconds (2018)

#310
post #177

Earlier quoted context omitted.

Yeah, maybe it's just having a more sensitive ear to the Scottish accent but that to me was the furthest from the reference by far.

I heard that too; being a Brit (and working in languages) probably helps. It did pick it up occasionally though, which gives hope that increased sampling and training could fix the slight miss there. It was that and the Swedish-accented English ("Sentence in Different Voices" section, middle recording) made it struggle. No traces of the Scandi-lilt were left in the synth version. Final note would be the French speake…

I can't hear any hint of an English accent in the French-language recordings, they just sound like regular Québec French to me.

However, I'm not convinced at all by these voice transfers across language. I can imagine the second Chinese one being the same speaker in both languages, but not the three others.

Post reply on HN