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

Voicebox: Generative AI model for speech that generalizes across tasks

ai.facebook.com

Post reply on HN
Print view View original

21–30 of 128 posts

Re: Voicebox: Generative AI model for speech that generalizes across tasks

#21

Post by twobitshifter »

ChuckNorris89 wrote: post #6
ChatGTP wrote: post #5

Is Meta just operating in hope and AI moonshots now ? Everyone one of their products is just garbage to me and becoming less relevant by the day. When do they actually starting building something useful again ? Honestly Apple seems to be using “AI” much more successfully and actually seamlessly integrating it into their existing products to improve them. My theory is Mark is hoping the meta verse will pop out if Yan’…

[flagged]

I think he’s talking about the new iOS feature that allows your text to be read in your own voice model.

Re: Voicebox: Generative AI model for speech that generalizes across tasks

#22

Post by ChuckNorris89 »

ChatGTP wrote: post #11
ChuckNorris89 wrote: post #6

Earlier quoted context omitted.

[flagged]

Do you use an iPhone ? They do pretty amazing things with images now. Even the search for a photo by text is quite amazing. I used it the other day for work for the first time and I found what I needed in my tens of thousands of photos. It almost truly felt like an extension of my memory, it was actually a pretty cool feeling. So sorry I don’t buy the Siri attack as being proof of anything. I have found Siri has impr…

Sent from my iPhone

Re: Voicebox: Generative AI model for speech that generalizes across tasks

#23

Post by twelfthnight »

canadianwriter wrote: post #3

That little stinger at the end was not as surprising as they thought it was :P It's very cool tech, but it's far from transparent. It has a very obvious "autotune" like sound to it that jumps right out. when they edited that one word it was obvious it had been edited. Again, super cool tech, just not going to replace voice actors or anything.

SPOILER ALERT :p

Its more surprising nowadays if an article about AI doesn't have a "twist" that what you read/heard/saw was AI.

Re: Voicebox: Generative AI model for speech that generalizes across tasks

#24

Post by theptip »

> As with other powerful new AI innovations, we recognize that this technology brings the potential for misuse and unintended harm. In our paper, we detail how we built a highly effective classifier that can distinguish between authentic speech and audio generated with Voicebox to mitigate these possible future risks. We believe it is important to be open about our work so the research community can build on it and to continue the important conversations we’re having about how to build AI responsibly, which is why we are sharing our approach and results in a research paper

Learning from the pushback on releasing LLaMA it seems. I wonder how hard this will be to replicate. (Trained on “60K hours of English audiobooks and 50K hours of multilingual audiobooks in 6 languages for the mono and multilingual setups”, this doesn’t sound intractable.)

Re: Voicebox: Generative AI model for speech that generalizes across tasks

#25

Post by tyrfing »

ChuckNorris89 wrote: post #6
ChatGTP wrote: post #5

Is Meta just operating in hope and AI moonshots now ? Everyone one of their products is just garbage to me and becoming less relevant by the day. When do they actually starting building something useful again ? Honestly Apple seems to be using “AI” much more successfully and actually seamlessly integrating it into their existing products to improve them. My theory is Mark is hoping the meta verse will pop out if Yan’…

[flagged]

Voice commands being usable is the one thing I miss from having an Android phone.

Re: Voicebox: Generative AI model for speech that generalizes across tasks

#26

Post by gwern »

rvz wrote: post #10

And the source code for this one has.... ...not been open sourced and cannot be found. Sorry AI bros. Better read the paper this time.

It won't be a big barrier. Voice stuff is not as computationally intense as video or LLMs, so it's still an area where small teams or hobbyists can make a dent.

Re: Voicebox: Generative AI model for speech that generalizes across tasks

#27

Post by pixl97 »

canadianwriter wrote: post #3

That little stinger at the end was not as surprising as they thought it was :P It's very cool tech, but it's far from transparent. It has a very obvious "autotune" like sound to it that jumps right out. when they edited that one word it was obvious it had been edited. Again, super cool tech, just not going to replace voice actors or anything.

For me its more like I wake up and check if humans have been replaced yet. Oh good, it's another day that I don't have to share one time pads with my mother to ensure that I'm talking to her and not a simulant performing fraud on a massive scale.
Post reply on HN