ChatGPT's voice closely resembles Scarlett Johnasson's, says lab analysis (www.npr.org)
from Potatos_are_not_friends@lemmy.world to technology@lemmy.ml on 01 Jun 21:38
https://lemmy.world/post/16072354

#technology

threaded - newest

autotldr@lemmings.world on 01 Jun 21:40 next collapse

This is the best summary I could come up with:


Actress Scarlett Johansson’s voice bears a striking resemblance to OpenAI’s now-pulled “Sky” personal assistant, according to an artificial intelligence lab analysis conducted by researchers at Arizona State University.

The researchers measured Sky, based on audio from demos OpenAI delivered last week, against the voices of around 600 professional actresses.

The lab study shows that the voices of Sky and Johansson have undeniable commonalities – something many listeners believed, and that now can be supported by statistical evidence, according to Arizona State University computer scientist Visar Berisha, who led the voice analysis in the school’s College of Health Solutions and the College of Engineering.

Berisha said while the study analyzed a vast array of subtle vocal features, it also zoomed in on several particular dimensions of each voice and teased out some differences.

Altman himself amped up the speculation on the day of the release by posting on X one word, “her,” the name of the 2013 romantic sci-fi film in which a lonely man falls in love with a superintelligent computer operating system voiced by Johansson.

The company says he deferred to OpenAI Chief Technology Officer Mira Murati, who told NPR she didn’t even know what Johannson sounded like until people were comparing Sky to the actress.


The original article contains 786 words, the summary contains 207 words. Saved 74%. I’m a bot and I’m open source!

Vendetta9076@sh.itjust.works on 02 Jun 01:05 next collapse

Fuckin shocker, the LLM company made something by smashing a bunch of data together and the output is similar to the input(s). Who would a guessed.

helenslunch@feddit.nl on 16 Jun 21:35 collapse

No it doesn’t.

Source: I mean just listen to it…