Great video. I love these topics of conversation. I also love the saxophone playing in the background. I studied AI and neutral networks at university many years ago. Since then the possible size of neural nets has grown significantly. Huge data centres now exist to train networks that are very deep and have lots of layers of modelled neurons. Each modelled neuron has weights and bias values that are fed into an activation function to determine what its output will be from the set of inputs that are fed to it from the prior layer. The weights and biases are finally settled on after all the epochs of the training iterations have been completed. The training uses techniques like the backpropagation algorithm and the gradient descent optimization algorithm to do this. Other algorithms have been developed more recently to improve the speed of training. In any event the neuron's weights and bias dictate what it's output will be for a given set of inputs. You can think of the network as a very huge set of gates. Ultimately the outputs from the neurons in the final layer (the output layer) is what forms the final resulting output for a given set of inputs at the initial input layer. You have to do some preprocessing in order to convert the input and expected output data pairs (music, images, text or whatever) into a form that can be given to the network for training purposes. Also after training is complete, when using it for generation purposes, you need to preprocess the user's input to feed it into the network and then you have to do some post processing of the generated outputs to convert the output into the target medium. I think actually these conversion processes are the most challenging aspect of using neural networks and that is certainly where Suno and Udio's intellectual property primarily reside. You have to do a really good job of curating the training data so that it is broadly representative of what you are trying to train it on so that you get a a more generally trained network that can respond reasonably well to inputs that it did not receive in its training data set. It's possible to overtrain a network resulting in overfitting to the detriment of the outputs it gives after training. An overtrained network is more likely to be less general and have a tendency to produce outputs that were in its training data. While I agree with you that neural networks do not sample in the strict sense of the word, I do believe that it is possible for them to represent the samples as patterns in the weights and biases of millions of neurons that are then reproduced by the postprocessing operation on the neural nets outputs. It's not sampling in the strict sense of the word but they are still reproducing it nonetheless, and it's still problematic from a copyright point of view. Also I wonder how well curated the training data set is for the training of these tools. Could it be that the data set is poorly curated and they were overtrained and that they have a nasty habit of spitting out over prevalent copyrighted artefacts that were in the training data e.g. producer tags?
@ronnenvallejo74442 ай бұрын
Thanks Paul. You’ve really inspired me to get into the both Suno and Udio and they’ve both been really fun and also eye opening. Your totally right though as you said in a previous video, It’s really a great idea tool more than anything, at least at this point. Thanks again.
@marcosazambuja2 ай бұрын
Hi Paul, I'm a brazilian musician/producer. When testing Udio, I thought "let's see if this service has a pop/hip hop bias, or if it can swing to latin american rhythms". So I prompted for some sambas. What I received back where a few tracks, and among them there were the voices of brazilian singers João Gilberto and (contemporary singer) Céu. It weren't similar voices, it were THEIR VOICES, with their articulation and style of interpretation. A fellow musician asked for brazilian music and received back a track with Daniela Mercury's voice, a very popular singer from Bahia (northeast of Brazil). So, I guess we have a situation here...
@YoPaulieMusic2 ай бұрын
I understand where you are coming from. I generated some of my own Brazilian bossa nova using Suno and, despite me pormpting it for a male vocalist, it came back with a gentle female voice similar to Céu. But, one could argue that Céu sounds similar to Astrud Gilberto... that style of gentle, almost child like female singing is quite popular in the genre. I was hoping to see if Suno would create a João Gilberto sounding song, but so far it has not. I've created songs in other genres that sounded similar to other artists, but they are not samples or direct copies.
@carcolevan71022 ай бұрын
The art that is from the AI obtained / contains none of the art on which it was trained.
@Musicmanbutte2 ай бұрын
That was a great video and thank you for clarifying that. The one thing, but at the end of the video you said it's up to the prompter to prompt AI to create an exact copy of a song. Can you do a video about how they would prompt the AI to create an exact copy of a song? I don't intend on recreating somebody else's song, but I'm just curious. I love the fact now that I can get all of the ideas out of my head with AI and as I left a comment in the previous video but it's due to my learning disabilities that I haven't learned how to play any instruments properly. But I would just like to know how a person would prompt an AI to create an exact duplicate of another song, I just mentioned I don't intend on recreating anybody else's music but I am just curious.
@YoPaulieMusic2 ай бұрын
I don't know how to do this, I'm hoping those that have done it will share their formula. I'm curious as to how much work is needed, my guess is a lot.
@Desirsar2 ай бұрын
The biggest thing that gets overlooked or not mentioned with AI "using math" is "statistics." They're language models just like ChatGPT, but have music elements as the "language" they output. A random seed picks a starting point, then it looks at its training and "thinks", "based on the tags I was prompted with, what's the likely next thing to be played in a song?" Sometimes it'll select a less common element, a lot like a raffle where the common thing has 50 tickets and everything else has one or two. The video topic that was popular for a week where people were generating weird covers of existing Christmas songs is a great example. If "christmas music" is the prompt, neither the music model nor the text model used for the lyrics has a huge selection of Christmas music it was trained on. Sure, tens of thousands of songs, but that's hundreds or thousands of covers of the same song over and over, because there just isn't that much original Christmas music. It goes to Paul's point about users intentionally prompting it to generate infringing works, it doesn't do that if you don't ask it to.
@Shyeep2 ай бұрын
People who say "Ai copies music" know that it isn't true.... but they are just trying to poison the well. They just want to reframe it as some sort of "immoral theft" so that they hope they can muddy everything and get it to stop or at least slow down. It's really sad how these people are fighting so hard against this amazing technology that offers the world SOOOO much in terms of art. All they care about is money and staying special and keeping the barrier to entry as high as possible.
@b.o.e.t.h.i.u.s2 ай бұрын
So glad you clarified that AI and humans learn the same way! I remember learning music in school, and you’re right, it happened just like it does with deep learning now. I never once played a piano, or joined a choir, or improvised on my instrument, or spent hours mastering centuries-old harmony and counterpoint techniques - but boy, I sure did steal a lot of CDs from the library, label and define each entire track in bland, cookie-cutter terms such as genre and style, then run them all through a ton of linear algebra calculations. Backpropagation was the hardest part, but that’s just how we humans learn! And now, just like AI, I’m still unable to think, feel, have an experience, dance, play a physical instrument, respond or interact with a crowd, analyze a score, create original forms, or explain anything at all about what I’m doing, but of course it’s still music. In fact the humans are the real fools and thieves here: jealous, entitled, attached to their bodies, environments and communities, as if these things really exist or matter, and can’t be equated with data inputs to a computer model!
@YoPaulieMusic2 ай бұрын
Your thoughts, feelings or experiences mean nothing to editors trying to find placeable music for their shows. But I appreciate your clever stretch of the concepts. AI ingests music, studies it, then reproduces it. Just like humans. The inner workings are different, but the main concept is the same. Thanks for taking time to participate in the conversation.
@peppepop2 ай бұрын
Well explained. Again ❤
@Sneakycat19712 ай бұрын
An advantage AI has is that it cannot only copy a particular style of music it can copy how the music was recorded. To me it looks like the AI is taking the MP3 or wav form and manipulating it into something different. It doesn't play the instruments in the AI generations, it manipulates the frequencies in the original recording into a different song but with the same sonics as the original recording .
@YoPaulieMusic2 ай бұрын
But, AI is not copying an individual song when you send a prompt. AI tools are trained on massive data sets to learn the rules of music from purely a waveform perspective. It then generates new waveforms based on those rules, not an analysis of a single song.
@Sneakycat19712 ай бұрын
@@YoPaulieMusic have you ever used Udio's upload feature? I'm willing to bet when you prompt the style of music you want it picks a random song in that genre and somehow manipulates the audio recording. I was using Suno a while back and heard a filtered out version of the song it was manipulating to make the song I prompted it to. It weird as hell
@GhostWriter_Music3 күн бұрын
AI copies the sounds used to create music, but uses a mathematical formula to create music, because music is math.
@DanyTomaslifeАй бұрын
No matter how much you like it or how you word it it is copyright infringement 101. But before keep arguing over wheter who's right or wrong I strongly suggest you find out the political agendas behind pushing Ai at all levels.
@Lethoscorpia2 ай бұрын
It sounds like copy alter paste multiple times from multiple sources much quicker than a human could do. Having listened to a Depeche Mode 'AI' track it sounded like a poor rip off with banal lyrics. I'll stick to the real thing thanks. Typing a few prompts can't compete with the joy of writing a great song yourself.
@candidbowyer46252 ай бұрын
How is your music real ? Is it played with real instruments for example ?
@Lethoscorpia2 ай бұрын
@@candidbowyer4625 yes I play several instruments sing and write my own songs. I also work with session singers and do cover versions. Even if 'AI' can produce music faster and better than mine I wouldn't use it. I'm not a major artist but I get a lot of pleasure from what I do.
@candidbowyer46252 ай бұрын
@@Lethoscorpia You write trance music (there's nothing wrong with that, I love trance) & you made a remix of Pachelbel's Canon in D major isn't that so ? Or were you talking about an original composition of yours also called Canon in D ?..........I listened to some of your music, I quite liked one of the trance tracks. I think a DJ would tell you it needs a much longer intro for mixing but that's fine, however I think you "copied" Pachelbel, & the music on your page is not "real" in the way most people would mean, real instruments played by humans it is not./
@Lethoscorpia2 ай бұрын
@@candidbowyer4625 kzfaq.info/get/bejne/ibeXla6B1sDOknU.htmlsi=9w4ZRcXECzt0eDSJ here I am playing my 'real' instruments I love all sorts of music. The tech changes over time I get that but typing prompts into a computer isn't for me.
@Lethoscorpia2 ай бұрын
@@candidbowyer4625 Here I am playing my 'real' instruments kzfaq.info/get/bejne/ibeXla6B1sDOknU.html but yes my trance music is more programmed or quantised on the computer and I do some covers you are right and some original compositions. Whereas my indie stuff is more me playing my instruments.