Artificial Intelligence makes music

Most pop music is pretty much produced using computers. Is ‘Algorithm Idol’ poised to take its place in the pop music mill? Pop music automation is a field of study among musicians and computer scientists with a goal of producing successful pop music algorithmically. It is often based on the premise that pop music is especially formulaic, unchanging, and easy to compose.The idea of automating pop music composition is related to many ideas in algorithmic music, Artificial Intelligence (AI) and computational creativity.

Now we have entered to the point that a Popular YouTube Artist Uses AI To Record New Album. Taryn Southern’s new single “Break Free” was composed by artificial intelligence. Actually the whole album I AM AI is claimed to be the first LP to be entirely composed and produced with AI. Southern used an open source AI platform called Amper Music to create the stems of “Break Free.” Actually AI is used also to make the following official music video for the “Break Free”. 

Break Free – Taryn Southern (Official Music Video)

The music track and video art were created using artificial intelligence, lyrics and vocal melodies written by by Taryn. Musician Taryn Southern on composing her new album entirely with AI article tells how artificial intelligence simplifies music production for solo artists and how it was used in the production. Southern used an open source AI platform called Amper Music to create the stems of “Break Free.” For each track, she plugs in genre, the instruments she wants to use, and beats per minute. In return, Amper churns out disjointed verses that can be rearranged into a song, and layered beneath Southern’s vocals. Toryn claims that you don’t need any knowledge of instrumentation to make a great song — you just need to have a good ear.

Amper Music Techstars Music LA Presentation 2017 Drew Silverstein

https://www.youtube.com/watch?v=rQjIFVNsTwc

Is this time for lots of new interesting or dull music?

More videos on AI music:

Flow Machines: can machines help us to be more creative?

Tutorial: Collaborating with an AI Music Producer

Google A.I. just created music (CNET Update)

Daddy’s Car: a song composed by Artificial Intelligence – in the style of the Beatles

Computer-Generated Jazz Improvisation

DeepBach: harmonization in the style of Bach generated using deep learning

Mr Shadow: a song composed by Artificial Intelligence

Links to more information:

OK computer: When pop music meets machine learning

From Jingles to Pop Hits, A.I. Is Music to Some Ears

Musician Taryn Southern on composing her new album entirely with AI

26 Comments

  1. Tomi Engdahl says:

    Daddy’s Car: a song composed by Artificial Intelligence – in the style of the Beatles
    https://www.youtube.com/watch?v=LSHZ_b05W7o

    Scientists at SONY CSL Research Lab have created the first-ever entire songs composed by Artificial Intelligence: “Daddy’s Car” and “Mister Shadow”. The researchers have developed FlowMachines, a system that learns music styles from a huge database of songs. Exploiting unique combinations of style transfer, optimization and interaction techniques, FlowMachines composes novel songs in many styles. “Daddy’s Car” is composed in the style of The Beatles. French composer Benoît Carré arranged and produced the songs, and wrote the lyrics. The two songs are excerpts of albums composed by Artificial Intelligence to be released in 2017. The research behind Daddy’s Car is financed by the ERC grant “Flow Machines”, Flow Machines is a project leaded by François Pachet and hosted by the Parisian University Pierre and Marie Curie. For more info: http://www.flow-machines.com/

    Reply
  2. Tomi Engdahl says:

    http://www.digitalmedia.fi/miten-kay-tekoalylta-rock-n-roll/

    Luovuus ei ole tekoälyn vahvin puoli, mutta onnistuisiko siltä silti uuden Beatles-hitin teko?
    http://www.hs.fi/kulttuuri/art-2000005193977.html

    Reply
  3. Eddie says:

    When I wake up I always listen to music. It make my feel fresh in the morning.

    Reply
  4. Tomi Engdahl says:

    Tutorial: Collaborating with an AI Music Producer
    https://www.youtube.com/watch?v=GIpI0Fus70A

    Tutorial: Composing with an AI Music Producer (Amper)
    http://www.joshuacasper.com/blog-post/ai-music-producer/

    Amper is an artificial intelligence composer, performer, and producer that empowers you to instantly create and customize original music for your content.

    Amper Music is an AI music producer that is currently free to use. In this video I show you how to use it!
    Amper Music uses intelligent programming to produce original music within a given set of parameters dictated by the user. Each track is unique, though not always great! I played around within the beta program for a while yesterday and was able to get a few good sounding tracks, however, more than that were unusable, at least in my opinion. I do, however, appreciate what is happening when using the program. It is all automated. It happens quickly. Truly incredible.

    The best thing about it is that the results are unique and you can use them! I make short videos for one of my projects and I am constantly looking for original music to put in the background. It has to be royalty free. I want it to be unique – not from the youtube music library that everyone has access to – and composing an original piece can take too long for how often I need it. This is a great tool for such projects.

    Reply
  5. Tomi Engdahl says:

    What is Amper Music? A Game Development Tool? Easy music creation for your projects – Amper Tutorial
    https://www.youtube.com/watch?v=x7Y6hufxdYU

    How’s it going everyone, in this Amper Music tutorial we take a look at this free beta web application. This is a great piece of software that let’s you quickly and easily create custom music tracks for your game.

    Reply
  6. Tomi Engdahl says:

    Music Track from Image Created by Artificial Intelligence
    https://www.youtube.com/watch?v=k1_Ojp8LY_o

    Reply
  7. Tomi Engdahl says:

    How to Generate Music – Intro to Deep Learning #9
    https://www.youtube.com/watch?v=4DMm5Lhey1U

    We’re going to build a music generating neural network trained on jazz songs in Keras. I’ll go over the history of algorithmic generation, then we’ll walk step by step through the process of how LSTM networks help us generate music.

    Reply
  8. Tomi Engdahl says:

    The 7 Steps of Machine Learning
    https://www.youtube.com/watch?v=nKW8Ndu7Mjw

    How can we tell if a drink is beer or wine? Machine learning, of course! In this episode of Cloud AI Adventures, Yufeng walks through the 7 steps involved in applied machine learning.

    The 7 Steps of Machine Learning
    https://medium.com/towards-data-science/the-7-steps-of-machine-learning-2877d7e5548e

    Reply
  9. Tomi Engdahl says:

    Programming an AI Companion for Piano Accompaniments
    https://blog.hackster.io/programming-an-ai-companion-for-piano-accompionments-ea0de44571a9

    Zack wanted to take a different approach: he wanted his AI to learn his style of playing, and then recreate it in real-time. Well-practiced musicians can do this on the fly, it’s the whole idea behind improvisational jamming. But, how does one teach a computer to do it?

    https://rpiai.com/piano/

    Reply
  10. Tomi Engdahl says:

    Raspberry Pi AI Plays Piano
    https://hackaday.com/2017/09/06/raspberry-pi-ai-plays-piano/

    [Zack] watched a video of [Dan Tepfer] using a computer with a MIDI keyboard to do some automatic fills when playing. He decided he wanted to do better and set out to create an AI that would learn–in real time–how to insert style-appropriate tunes in the gap between the human performance.

    If you want the code, you can find it on GitHub. However, the really interesting part is the log of his experiences, successes, and failures.

    https://github.com/schollz/PIanoAI

    https://github.com/schollz/PIanoAI

    Reply
  11. Tomi Engdahl says:

    Jamming with PIanoAI (clip #2) (Version 1.0)
    https://www.youtube.com/watch?v=vF0uQax56a4

    Another example of a teaching (~30s) and then alternating jamming with piano. The AI becomes better over time.

    Reply
  12. rahul mehta says:

    Thanks for this nice work

    Reply
  13. Tomi Engdahl says:

    Diehard Fans Turn Virtual Teen Singer into Japanese Mega-Star
    https://www.bloomberg.com/news/articles/2017-10-29/diehard-fans-turn-virtual-teen-singer-into-japanese-mega-star

    She wears extremely short skirts, sports blue pigtails to her knees and has the boundless energy of a playful puppy. During her 10-year career, she’s released more than 100,000 songs in a variety of languages and opened shows for Lady Gaga.

    And yet Hatsune Miku, who boasts 2.5 million Facebook followers, doesn’t actually exist — at least not in the typical way we think of a flesh-and-blood diva.

    Miku is a computer-simulated pop star created more than a decade ago by Hiroyuki Ito, CEO of Crypton Future Media in Sapporo, Japan. She started life as a piece of voice-synthesis software but since has evolved to become a singing sensation in her own right — thanks to the creativity of her legions of fans.

    Reply
  14. Tomi Engdahl says:

    Funny how the man-made lyrics are the weakest part of this

    Reply
  15. Tomi Engdahl says:

    Two Technologists Create Black Metal Album Using An AI
    https://m.slashdot.org/story/334373

    Coditany of Timeness” is a convincing lo-fi black metal album, complete with atmospheric interludes, tremolo guitar, frantic blast beats and screeching vocals. But the record, which you can listen to on Bandcamp, wasn’t created by musicians. Instead, it was generated by two musical technologists using a deep learning software that ingests a musical album, processes it, and spits out an imitation of its style.

    https://theoutline.com/post/2556/this-frostbitten-black-metal-album-was-created-by-an-artificial-intelligence

    Reply
  16. Tomi Engdahl says:

    When neural nets do carols: ‘Santa baby bore sweet Jesus Christ. Fa la la la la la, la la la la’
    A truly AI Christmas to one and all + El Regmas song
    https://www.theregister.co.uk/2017/12/22/neural_network_christmas_carols/

    What is this latest madness? you may ask. Well, it’s 2017 and it’s Christmas so someone has obviously had a crack a training a neural network to write carols.

    The results are at least entertaining, even if they might offend the devout – or simply those not keen on the idea of Santa popping out a baby Jesus or people getting it on with snowmen.

    Christmas Carols, generated by a neural network
    http://aiweirdness.com/post/168770625987/christmas-carols-generated-by-a-neural-network

    Reply
  17. Tomi Engdahl says:

    ICT
    ‘Earworm melodies with strange aspects’ – what happens when AI makes music
    https://horizon-magazine.eu/article/earworm-melodies-strange-aspects-what-happens-when-ai-makes-music_en.html

    The first full-length mainstream music album co-written with the help of artificial intelligence (AI) was released on 12 January and experts believe that the science behind it could lead to a whole new style of music composition.

    Popular music has always been fertile ground for technological innovation. From the electric guitar to the studio desk, laptops and the wah-wah pedal, music has the ability to absorb new inventions with ease.

    Now, the release of Hello World, the first entire studio album co-created by artists and AI could mark a watershed in music composition

    Stemming from the FlowMachines project, funded by the EU’s European Research Council, the album is the fruits of the labour of 15 artists, music producer Benoit Carré, aka Skygge, and creative software designed by computer scientist and AI expert François Pachet.

    ‘The system … analyses the music in terms of beats, melody and harmony,’ said Pachet, ‘And then outputs an original piece of music based on that style.’

    ‘The core (problem) was how to do that so that (it) takes into account user constraints. Why? Because if you compose music, actually you never do something from scratch from A to Z,’

    Reply
  18. Sonam says:

    Very Impressive AI tutorial. The content seems to be pretty exhaustive and excellent and will definitely help in learning AI course. I’m also a learner taken up AI training and I think your content has cleared some concepts of mine. While browsing for AI tutorials on YouTube i found this fantastic video on AI. Do check it out if you are interested to know more.https://www.youtube.com/watch?v=KlU6w7bbw0o

    Reply
  19. Sonam says:

    What a fantastic read on AI. This has helped me understand a lot in AI course. Please keep sharing similar write ups on AI. Guys if you are keen to know more on AI, must check this wonderful AI tutorial and i’m sure you will enjoy learning on AI training.
    https://www.youtube.com/watch?v=KlU6w7bbw0o

    Reply
  20. slot joker pulsa says:

    This is the news!!! Artificial Intelligents usage in a unique ways. Last time I knew, AI can only be used to automatically control any game program, Like, control action of Mobile Legends creeps

    Reply
  21. Tomi Engdahl says:

    “The track and cover artwork is built with AIs and neural networks extracting the core melodic and textural essence of thousands of 80ies pop and soundtracks, and styled with retro-wave, synth and trap-goth elements. The chorus voices are built with digital reproduction tools of all the speech synthesis tools of the 80ies.”

    http://www.ugress.com/static-troopers/?fbclid=IwAR1TeMcsqqB_vUkNzbjH8Xm6NqzC4k6fhqQI2j1tyU6FfrS14jmLRxEYBs4

    Reply
  22. Tomi Engdahl says:

    The future of AI in Music Production
    https://www.youtube.com/watch?v=xgtap6_Whbw

    Viewer comments:

    AI has its place. If it speeds up the process for mixing and getting the same results as 100% manual then all good.

    Your prediction for music becoming generic has already happened via AI, although not as directly. AI informs the music industry regarding demographics, what sells the most, what sells the least, and the industry has responded by trying to create more of the style that sells the most. This results in cookie-cutter artists that mostly occupy the pop music genre. AI used as you describe may eliminate the need for human producers in the pop genre. That may be a good thing for music, because the great producers may be forced to work with less mainstream artists, helping these artists compete sound-wise.

    We’ve had computers design a lot of our custom DSP algorithms, even 10 years ago. It is unfortunate how AI / ML has become kind of like a sticker on product packaging, like it was a selling point on its own merit. Plugins should be judged by their acoustic performance & features and not the under-the-hood stuff which is really meaningless to the end user, and is also repeatedly demonstrated to be exploited by the fact that truthfulness of such inner details can’t really be verified.

    Reply
  23. Tomi Engdahl says:

    Chloe Xiang / VICE:
    A look at AI Hub, a Discord community focused on AI music that released an entire album featuring original songs using AI-generated vocals from famous artists

    Inside the Discord Where Thousands of Rogue Producers Are Making AI Music
    On Saturday, they released an entire album using an AI-generated copy of Travis Scott’s voice, and labels are trying to kill it.
    https://www.vice.com/en/article/y3wdj7/inside-the-discord-where-thousands-of-rogue-producers-are-making-ai-music

    Reply
  24. Tomi Engdahl says:

    Martine Paris / Forbes:
    Pop star Grimes tells fans to create AI-generated music using her voice, saying she will split 50% royalties, the same deal as “with any artist I collab with”

    Grimes Tells Fans To Deepfake Her Music, Will Split 50% Royalties With AI
    https://www.forbes.com/sites/martineparis/2023/04/24/grimes-tells-fans-to-deepfake-drake-her-welcomes-collaboration-with-ai/?sh=575d223f15c0

    In the wake of the AI-generated hit Heart on My Sleeve going viral with deepfakes of multi-platinum artists Drake and The Weeknd, pop star Grimes has invited her fans to create music with her voice.

    On Sunday night she tweeted, “I’ll split 50% royalties on any successful AI generated song that uses my voice. Same deal as I would with any artist i collab with. Feel free to use my voice without penalty. I have no label and no legal bindings.”

    She added that she’s open to anything anyone wants. “Im just curious what even happens and interested in being a Guinea pig,” She said she welcomes the open sourcing of art and an end to copyright.

    A position in sharp contrast to Universal Music Group which moved swiftly to take down Heart on My Sleeve across social media and music services like Spotify, Tidal and Apple Music as the song started to climb the charts earlier this month.

    “UMG’s success has been, in part, due to embracing new technology and putting it to work for our artists–as we have been doing with our own innovation around AI for some time already,” the company explained in a statement to Variety. “With that said, however, the training of generative AI using our artists’ music (which represents both a breach of our agreements and a violation of copyright law) as well as the availability of infringing content created with generative AI on DSPs, begs the question as to which side of history all stakeholders in the music ecosystem want to be on: the side of artists, fans and human creative expression, or on the side of deep fakes, fraud and denying artists their due compensation. These instances demonstrate why platforms have a fundamental legal and ethical responsibility to prevent the use of their services in ways that harm artists. We’re encouraged by the engagement of our platform partners on these issues–as they recognize they need to be part of the solution.”

    Facing the inevitable

    Grimes has long embraced AI as a techno artist. In 2020, her first album to top the Billboard dance charts was Miss Anthropocene, named for the effects of technology on Earth’s ecology and climate in the post-Industrial Revolution era.

    It was also in 2020 that she teamed up with the algorithmic mood music startup Endel to create an AI-generated lullaby for her first child with SpaceX founder Elon Musk who they named X Æ A-12 with the Elven spelling of AI, according to Grimes.

    “Everyday I thank the overlords of Ableton for cleaning up my tracks, but I do worry though that AI will outpace us and make musicians obsolete. It’s inevitable,” she warned at Web Summit 2020.

    With millions of followers across YouTube, Instagram and Twitter and hits like Oblivion, Kill V. Maim and Go, her call for AI collaboration could be a game changer.

    Deepfakes are wildly popular on TikTok.

    There’s even a bot on Telegram called Forever Voices created by tech founder John Meyer who has trained the AI to copy the speech and tone of celebrities and has enabled fans to chat with it via the ChatGPT API. See the CNBC demo below.

    Grimes’ voice is now available to chat with, Meyers confirmed Monday afternoon. “We’re looking into supporting singing,” he said.

    Reply

Leave a Comment

Your email address will not be published. Required fields are marked *

*

*