News for hackers. Stuff that matters.
Re:Noise2Music: Generating Music from Text Using Diffusion M... by Hydraulix989 on Sunday January 29, 2023 @04:49AM (#34566527)
"AI plagiarism" spotted.

The Spectrogram Model for #23 prompt "It sounds energetic and like something you would hear in clubs." sounds almost EXACTLY like "Psy - Gangnam Style"...

The model is hallucinating what it was trained on.

Re:Noise2Music: Generating Music from Text Using Diffusion M... by Oranguru on Sunday January 29, 2023 @06:50AM (#34567232)
Hallucinating? you mean overfitting, right?
Re:Noise2Music: Generating Music from Text Using Diffusion M... by mensetmanusman on Sunday January 29, 2023 @07:23AM (#34567447)
You mean like most pop music?

https://youtu.be/9oCgSE-Le0c

Re:Noise2Music: Generating Music from Text Using Diffusion M... by williamcotton on Sunday January 29, 2023 @07:41AM (#34567559)
I mean, I can sort of hear it, but there's enough of a difference that it's still original, if not musically derivative... but this is electronic dance music we're talking about! If people are going to a French House night they expect something musically derivative! The genre depends on seamlessly mixing various works together so there has to be an incredibly amount of similarities.
Re:Noise2Music: Generating Music from Text Using Diffusion M... by Hydraulix989 on Sunday January 29, 2023 @05:39PM (#34573534)
Are you sure? I can hear Psy's voice and recognize the lyrics.
Re:Noise2Music: Generating Music from Text Using Diffusion M... by williamcotton on Monday January 30, 2023 @11:27AM (#34582005)
I've been going through Gangnam Style in detail and the more I compare the two the more I find that they are very different.

Guilty of terribly trite, cliched and overall bad music, but not guilty of plagiarism.

Re:Noise2Music: Generating Music from Text Using Diffusion M... by Hydraulix989 on Wednesday February 01, 2023 @01:18AM (#34607125)
You must not be very musically inclined then. I am a professionally trained musician. You need a good ear to spot the rhythmic similarities.
Re:Noise2Music: Generating Music from Text Using Diffusion M... by taybeck on Thursday February 02, 2023 @04:53PM (#34633718)
I thought the same exact thing upon listening to #23. It's pretty obviously using elements from it IMO, even though it's layering and warping them. Hard to prove though...