Jukebox • Hacker News Board

Re: Jukebox

#81

Post by misiti3780 » Thu, Apr 30, 2020, 9:36 PM UTC

frank2 wrote: post #71

misiti3780 wrote: post #70

I cant wait till we inevitably see a #1 hit that is NN generated. Interesting question is who will get paid?

IANAL, but it strikes me as pretty obvious that the owner of the NN is the owner of the copyright on any works created by the NN with the important qualification that training the NN on works copyrighted by others could possibly be considered by the courts to be infringement.

Sure, but imagine a scenario when I use transfer learning. I download a pretrained model from OpenAI, make some tweaks, maybe train it on my own music, and have a michael jackson level triller hit?

Re: Jukebox

#82

Post by Kiro » Thu, Apr 30, 2020, 9:44 PM UTC

ihm wrote: post #50

In my view, attempts like this misunderstand much of the point of music. That is, to communicate aspects of human life that are deeply interwoven with facts and experiences outside of the music itself. I don't see how any of that will be possible before we have some kind of general AI, and in the meantime I think these attempts will continue to be semantically empty, even unsettling in their emptiness.

> That is, to communicate aspects of human life that are deeply interwoven with facts and experiences outside of the music itself.

What does that even mean? As a counter-point I listen to heavy bass music with zero lyrics. The production value is the most important thing for me and I would 100% listen to AI generated music.

Re: Jukebox

#83

Post by somebodythere » Thu, Apr 30, 2020, 9:47 PM UTC

frank2 wrote: post #71

misiti3780 wrote: post #70

I cant wait till we inevitably see a #1 hit that is NN generated. Interesting question is who will get paid?

IANAL, but it strikes me as pretty obvious that the owner of the NN is the owner of the copyright on any works created by the NN with the important qualification that training the NN on works copyrighted by others could possibly be considered by the courts to be infringement.

In the United States, there was case that got a decent amount of publicity where the opinion was that training a model on copyrighted works is "highly transformative" and is therefore permitted under fair use.

https://towardsdatascience.com/the-most-important-supreme-co...

Re: Jukebox

#84

Post by gavanwoolery » Thu, Apr 30, 2020, 9:50 PM UTC

This is really great work. :) On a slightly tangential note, I understand why they chose an audio representation over symbolic, but I think that training the latter is more useful (commercially speaking). Would love to be able to get a track rolling quickly just selecting an instrument set and tweaking some AI parameters and then hand-tune it from there (yes, this greatly detracts from the "art" of it but sometimes I just want to see results quickly). Of course, to do this effectively, you would also have to analyze on an audio level (at least per instrument) so that the usage and timing of instruments could be better understood.

Re: Jukebox

#85

Post by corysama » Thu, Apr 30, 2020, 9:57 PM UTC

nabla9 wrote: post #5

I predict that in very near future you just write funny lyrics, select the style and vocalist you want and you get good sounding mediocre music. Then we hear it in - private events like weddings. - social media creators make their own music to go with their funny videos. Cheap theme music for streamers and podcasters. - Advertising. Shopping centres make lyrics that advertise products and play them to you as pop song…

With http://songsmith.ms/ from Microsoft Research you just sing whatever and it tries to fit cheesy, casio-keyboard music to your mumbles to make it sound like you planned it. Of course, the real fun is taking vocals from popular songs and making casio-keyboard covers https://www.youtube.com/watch?v=wTN-ixHQ2hM

Re: Jukebox

#86

Post by nzoschke » Thu, Apr 30, 2020, 10:09 PM UTC

If you want to play with a more literal jukebox, check out https://play.getjukelab.com in desktop Chrome with a Spotify premium account.

This is part of a fun side project a friend and I hack on and throw occasional parties with: https://getjukelab.com/

Re: Jukebox

#87

Post by derefr » Thu, Apr 30, 2020, 10:13 PM UTC

dellinspiron wrote: post #61

I think people in the comments are completely missing the point of this work. As I understand it, and take this with a large grain of salt because I haven't read the paper, the idea of Jukebox is to take a certain style of music by a certain musician and have the algorithm sing, karaoke-style, the lyrics that are listed in the examples to the tune of that music. Think of it as a really jazzy version of Google text-to…

> It's hilarious how as soon as there's some new AI work done everyone starts wailing, "where's the humanity!"

Lay-people think AI refers to ALife.

Most of the talking heads would be immediately satisfied—giving none of these complaints—if they were shown an "AI" program that responds to stimuli by entering emotional states, and which learns to associate stimuli with the emotional states it has been in in the past, such that those stimuli will then become triggers for those states, and for memories associated with those states.

Such an agent wouldn't even need to use ML techniques, necessarily. It'd just need to be a high-concept tamagotchi that can respond to operant conditioning. That would already be an advance over the state of the art.

But, AFAIK, nobody's really working on ALife in the sense of "making an individual agent with a complex-enough internal model that it can statefully respond to you the way a pet does." ALife is only really studied at the very low level (C. Elegans connectome simulation) or the very high level (sociological/economic simulations using simple goal-driven agents); nobody's really working in the space "in between." (Except for the people trying to make chat bots seem friendlier, but they're mostly trying to fake it, rather than creating actual persistence-of-memory.)

I wonder why nobody's interested in medium-scale ALife research these days? It used to be a hot topic, back when it was conflated with robotics under the banner of "embodied cognition."

Re: Jukebox

#88

Post by caetris1 » Thu, Apr 30, 2020, 10:18 PM UTC

corysama wrote: post #85

nabla9 wrote: post #5

I predict that in very near future you just write funny lyrics, select the style and vocalist you want and you get good sounding mediocre music. Then we hear it in - private events like weddings. - social media creators make their own music to go with their funny videos. Cheap theme music for streamers and podcasters. - Advertising. Shopping centres make lyrics that advertise products and play them to you as pop song…

With http://songsmith.ms/ from Microsoft Research you just sing whatever and it tries to fit cheesy, casio-keyboard music to your mumbles to make it sound like you planned it. Of course, the real fun is taking vocals from popular songs and making casio-keyboard covers https://www.youtube.com/watch?v=wTN-ixHQ2hM

This is truly great on so many levels. The cheesy sarcastic late night infomercial demo is artistry. Thanks for sharing this.

Re: Jukebox

#89

Post by dimmuborgir » Thu, Apr 30, 2020, 10:21 PM UTC

ihm wrote: post #50

In my view, attempts like this misunderstand much of the point of music. That is, to communicate aspects of human life that are deeply interwoven with facts and experiences outside of the music itself. I don't see how any of that will be possible before we have some kind of general AI, and in the meantime I think these attempts will continue to be semantically empty, even unsettling in their emptiness.

Who gets to decide what is the "point" of music? Music is a twenty billion dollar industry. An AI system that can spit out highly "realistic" and "pleasing" music can change the music industry as we know it.

Re: Jukebox

#90

Post by nmca » Thu, Apr 30, 2020, 10:36 PM UTC

dellinspiron wrote: post #61

I think people in the comments are completely missing the point of this work. As I understand it, and take this with a large grain of salt because I haven't read the paper, the idea of Jukebox is to take a certain style of music by a certain musician and have the algorithm sing, karaoke-style, the lyrics that are listed in the examples to the tune of that music. Think of it as a really jazzy version of Google text-to…

You misunderstand critically that this is not "singing along", it's generating the music and voice. Conditioning on lyrics is optional, and done "unaligned", eg by arbitrarily encoding the lyrics and passing them as additional input.