Nvidia Fugatto: "World's Most Flexible Sound Machine"
blogs.nvidia.com
blogs.nvidia.com
In general I think that with ai generated audio it is much more noticeable how utterly bad everything is, that ai generates. I already absolutely hate the two AI voices that are in a lot of YouTube videos and are a reason for me to close the Video immediately most of the time.
Here's another example on the Suno website: https://suno.com/song/fc991b95-e4e9-4c8f-87e8-e5e4560755e7
I think this is why there is no real, powerful protest against all that generated stuff. Only the people, that care, are able to articulate what's wrong with it. To me, all of AI generated content sounds horrible. To almost everyone else, this sounds ok. So we will see and hear more of this generated stuff. We are in the middle of the enshittification of all consumable media.
Why go on tour if you can send an AI singer instead and if you cannot sing as good as it anyway?
Most human musicians have very little power; that's been going away for a long time, even since "canned music" "robots" pushed live bands out of cinemas a century ago: https://www.smithsonianmag.com/history/musicians-wage-war-ag...
Most popular music already feels, and to an extent is, fake. Not only because mere recording allows repeated takes until it's inhumanly "perfect".
When I played an MP3 of Britney Spears to my mum around the turn of the century, she thought it was a robot singing because of the autotune.
The Monkees was famously an attempt at a manufactured band whose members just happened to not feel like playing that game and did it for real, Gorillaz is even more obviously manufactured. Parasocial relationships are inherently different from "real" relationships, but the performers have to pretend that it's personal when they address a crowd or a camera.
Axis of Awesome demonstrated the similarity of most modern hits with their "4 Chords": https://youtu.be/oOlDewpCfZQ?feature=shared
Those with the power were, possibly still are, the record labels; but if the AI are trained on the works of small musicians that can't afford the copyright cases or the political influence, but also whose works are not under the umbrella of the labels who do have those resources but not the right or short term motivation to intercede on their behalf, the big labels themselves may lose the consumer market to free AI output, while professionals will dismiss both the AI output and the label's output as "just different kinds of slop but both slop" (or whatever the current insult de jour is for AI).
I'm starting to think that what AI might be replacing is high ends of consumption, not low ends of generation. Arts has followers that are often less historically significant than genre pioneering works. Doesn't that seem like what AI is doing?
Listening on a laptop speaker Sumo sounds fine. Listening on my wireless earbuds it is... ok. I am too lazy anymore to pull out any of my high quality wired headphones, and if somebody who used to care about sound quality enough to purchase multiple HQ headphones can't be arsed, then the general pubic really is going to think everything is just fine.
Generative AI outputs trigger uncanny valley discomfort that professionals and connoisseurs are better equipped to verbalize.
The quality question is what's the point of stuffs like that, or is it good, even safe, for us to consume.
I've listened to both songs on my Bose QC ultra headphones, which are far from perfect headphones. But even on them, the female voice has unbearable resonances in the higher frequencies. The male voice sounds mostly ok, but has also something that sounds like compression artifacts (like mp3 compression, not loudness compression). All instruments in these songs have these problems. They sound somewhat like the real thing, but really badly recorded. Also, the mixing isn't any good.
It is still very impressive that AI can generate that. But if I would record my band and someone would create such a mix out of it, I would fire them immediately. Heck, I would be furious that they fucked up so bad and would try to get my money back.
So the two links you provided just confirm what I said.
That said, I mostly prefer AI over "real" human-made recordings (pop, classical, metal, bardcore, whatever) because I tend to learn the patterns too fast to enjoy, or really even tolerate, any recording more than about 3 times* — I assume I'd like live jazz for longer, but have only been to one place that ever had it so I don't know if it breaks that pattern.
* sole exception: TV theme tunes, though the point of them isn't to listen to them
> Imagine forcing an artist to unlearn
Mathematical models cannot learn. What happens in fact is the owner of generative AI takes a bunch of copyrighted works which took a lot of effort and money to produce (instruments, mics and other equipment is super expensive), puts it into computer and sells whatever the computer has calculated from those recording. Do you see any learning or any creativity here?
There were cases when suno (or udio) was reproducing producer tags almost verbatim (but in lower quality) for example. This shows that the model was not simply calculating some probabilities of patterns of pitches, durations etc, but was storing the copyrighted content almost unmodified.
Also, personally I have no interest in a service that generates a song for you because it takes away all the fun. Maybe something that helps to find mistakes in composed music and help learning would be much more useful.
> Also, personally I have no interest in a service that generates a song for you because it takes away all the fun. Maybe something that helps to find mistakes in composed music and help learning would be much more useful.
You are not forced to use the full raw output, you could use it sparingly in your new composition, the same way you might use ChatGPT to improve your lyrics.
All non-musician friends where thrilled to generate music. It's already extremely fun and will keep getting better. I think it lowers the barrier of entry and will increase the total amount of performers, the "real" musicians. I am sure musicians playing instruments back in the days had the same idea about digital music: "Not playing with the physical instruments takes away all the fun. You can't touch, smell, feel it. It has a negative impact on the music and on the people. I am so smart, I am a democrat, you guys are nazis, you want to destroy humanity while I want to restrict the majority of the people from having fun.".
> lot of effort and money to produce Mathematical formulas too, and you can't copyright them.
If a new device is invented to replay memory "almost verbatim (but in lower quality) for example". Should its use be restricted with regard to copyrighted content? It's your memory, your unique interpretation, shouldn't it belong to you?
AI will get better and you'll be able to easily go up the tree from which content was derived (intentionally or not) based on the similarity and the publication date.
Artists don't need more protections than mathematicians.
Of course not if we take it to the extreme, ie only copyrighted work reproduced almost identical, but I've used the platform with my own music and it reorganized it in a very interesting way, actually inspiring new songs and arrangements which I'll probably play with real instruments. I haven't the slightest interest in replicating top chart garbage; however lawsuits by major labels are ruining also the creative aspect where no copyrighted work is involved. Suno is now quite likely retraining their model only on free music because of the lawsuits, and despite the hype, for some genres last version turned out awful.
Sorry, but I'm pessimistic. If we don't change how AI regulation works, pretty much every creative field will be ruined by greedy tech companies and their planet-burning plagiarism devices.
[1] https://d1qx31qr3h6wln.cloudfront.net/publications/FUGATTO.p...
Available music generation models sound much more musical and have much better diction on vocals.
There are sample-based virtual instruments, but they do miss some subtleties, and there are physics-based ones where some subtleties are preserved, but generally worse sounding because actually modelling real hardware evolved over centuries is really difficult.
Even hardware-based instruments like electric guitars/violins/cellos etc. generally sound distinct from and less interesting than their acoustic counterparts. Electric guitar players seem to use various amplifier tricks to make up for that, and that's now a big separate instrument. But I think the point stands.
But what about an AI guitar that automatically frets the strings properly if you don't press them hard enough? Or an AI piano which shifts the keyboard when it sees that you are about to hit the wrong key?
Many instruments require lot of practice before you can produce acceptable sound. Can AI help with this?
My sense is that contrary to marketing, ai tools will be most useful to people who already have musical skill and will actively subvert musical development in most people who rely on it too early in their process.
It's a corporate dream: a thing that spews barely-passable, generic mush that's totally aligned with demands of the decision makers, but has zero opinion, zero ambition, zero professional pride and no need to uphold its ethical and aesthetic standards and its own reputation whatsoever.
Instead of tools for the creatives we have systems that generate complete tracks from tinder chat logs. On the other hand, there's still no publicly available audio style transfer with even remotely usable quality (that thing from Google is abysmal).
All I want for starters is something that turns a slightly distorted, over-reverberated and not-perfectly intonated flute recording that a client sends me into a clean workable track. I don't even ask for it to turn it into koto or marimba or whatever you think is a cool demonstration case!
Sorry for the rant, but it's all very frustrating and alarming.
The headphones aren't on the ears — a surprisingly common error even in pre-AI human-made cartoons.
As a professional monkey in front of a computer, I feel offended.
Disclainmer: I prefer dogs, they are more friendly and even part of the family, but I have to recognize that cats look more cool.