Exploring Aspects Of AI Music Generation

Cartoon Music Machine by AI

Image collage created by AI via Bored Humans website

This post is really just an attempt of mine to gather together some of the explorations I have been doing to see what progress is being made with AI technology and the making of music and sound. It’s all pretty strange worlds out there right now.

Some sites are starting to use inputted text from users to generate sound and music. Others are built where the user does not have agency to create music, only to experience songs based on some choices, like mood or genre or artist. None of it, to my ears, sounds authentically human (yet?).

Here are a few sites I’ve explored:

Riffusion takes a phrase of writing put into its engine and moves it into a sort of song pattern, and the site features a rolling musical pattern that is designed to make visual the algorithmic patterns being used. Here is one that I did for a Daily Create that featured Riffusion with the phrase: A haiku is a moment in time. See the details on how Riffusion works — it is pretty fascinating. (Free to use)

Google is developing its own text-to-music AI generator, called MusicLM, which takes inputted text and creates a moody, evocative soundtrack to go with the words. There are plenty of intriguing examples, although it seems like Google is maybe working to figure out the copyright logistics of its database, where it has collected sound and loops that its machine uses to generate the soundtracks from text. Google also has the Magenta Project, another AI development that’s been around for bit, and the Magenta site does feature some examples of how it is being used to merge creativity with machine learning. (MusicLM not yet publicly available for use other than samples – Magenta data can be used for projects, I think)

OpenAI — the group behind ChatGPT — has Jukebox on its drawing board, and the algorithms are being fed music and sound and song lyrics, and it is learning how to create music tracks in the styles of those artists. It’s a bit jarring, to me, to hear how the machine uses Ella Fitzgerald as its source. OpenAI also has something called MuseNet, which seems similar to Jukebox. (Not yet publicly available other than samples)

The Bored Humans website has an AI Music Generator that uses neural network learning to produce entirely computer-generated songs, with lyrics. None of it is much fun to listen to for any extended period of time, in my opinion, but that it is being done is something to take note of, and worth playing around with. They even host a Lyric Generator.  (Free to use)

Soundraw is a site that generates music by mood, and gives you a handful of song options to choose from. I found many of the tracks sounded the same, but I didn’t do a full explore of the possibilities there. Here is a track for the mood of “hopeful” as an example. (Free to use, but requires account for any download)

Melobytes is another odd one, but it gives you plenty of options to manipulate the sounds the AI generates as a sort of “song” from text — although every time I have used Melobytes, the song sounds pretty jarring and off-kilter to me. (Account required).

And I am sure there are others out there, too, and more to come, no doubt.

Whether this is all good for the field of music creation or not will be debated for a long time, I am sure. Just as ChatGPT and its field of chatbots has many thinking deeply on the art and creative act of writing, so too will the field of AI music generators have musicians wondering about how the field of sound is being transformed by algorithms, and what it means to be an artist in the field of music. (I also worry these AIs will put a lot of musicians who work on films and television and other media venues out of work, just as the DJ put many live bands out of work for weddings and other gigs.)

Peace (and sound),
Kevin

 

The Crazy Dictionary Project: Word Invention And Multi-Year Collaborations

Words of 2023

Each year, as part of a unit around exploring Word Origins with my sixth graders, they invent new words and then donate one of their words to an ongoing project we call the Crazy Collaborative Dictionary — it started in 2005 and every single year (except for the Pandemic Year), students add to the project, collaborating across time.

Listen to this year’s student word creators reading their words, definitions and sentences. We add audio files to keep their voice connected to their words. The word cloud above is a collection of words submitted this year.

We’re in the process of adding this year’s contributions to the dictionary, and the dictionary itself is in the midst of some audio file movement, so not all links at the dictionary itself are working for the voice files.

Here is link to the dictionary (now hosted at my old classroom blog space_ and a link to the master folder with all audio files from across the years of recording.

Peace (and Words),
Kevin

Is Making Music With The Machine The Same As Writing With The Machine?

Music Machine
Music Machine flickr photo by Dogtrax shared under a Creative Commons (BY-SA) license

My connected friend, Maha Bali, shared a post about thinking through how to navigate the world of citation in the age of ChatGPT and AI-generated text, particularly if a writer uses the AI chat for parts of their own writing and/or research. Maha suggested a citation format, but I was particularly intrigued by Alan Levine’s thoughtful response in the comments, and when Alan referenced Jonathan Portiz’ insights about how or whether to reference machines in the act of writing, using the use of music software for songwriting as an example, something perked up for me.

(See Maha’s post and the comments at the bottom and then her follow-up post)

I like to write and produce music, mostly at the hobby level. Although I do play real instruments (saxophone and rhythm guitar, and I also dabble with bass and keyboards), I also often turn to apps and platforms like Garageband and Soundtrap, and use sound loops and other elements of the computer to create music.

When I have shared those pieces out, I have often wrestled with how to make sure anyone listening (if anyone is even listening) would know it wasn’t me playing those instruments, but some musical loops. Often, of course, it’s obvious, mostly because the music comes out rather way too flawless and always exactly on the beat, like a droning metronome. That said, it’s not always obvious that technology has been used. If I am layering in my own singing voice, or my saxophone, or guitar into the mix, then the hybrid pieces are a bit of both things — the human musician and the algorithmic loops.

I have yet to come to a suitable system for letting anyone listening know that a piece of music is more computer loop than musician me. To be honest, I often travel the lazy route — no mentions of the software.

Here’s an example of what I mean. A music friend had sent me some lyrics and asked for a song, which I then built musically in Garageband after adding some lyrics to his words myself, so it’s a human-human-machine collaboration. When I shared the final version with him, he admired my guitar playing, to which I let him know the reality – none of it was me.

So this topic of leaning on the machine for creativity, and whether to make that kind of technical support more visible to others in any published content through citations or some other methods, has long been at the back of my mind.

This has been made more pertinent in recent years as my teenage son has been producing his own music tracks using another (more advanced) digital music software platform, collaborating with hiphop singers and writers from around the world. He doesn’t play an instrument. He plays the platform. He doesn’t cite the platform when he posts his music on the major streaming services.

Should he be considered a musician, even though he didn’t make any of the original loops himself? What about if he edits and changes the loops, as he does? Should every loop he uses be cited somehow?

All this brings us to ChatGPT and its brethren, and Maha’s exploration of how to make citations when using AI chat platforms for writing pieces.

Is it necessary to cite the machine?

My initial impulse is that Maha’s discussion about writing and citation feels different from making songs because it is writing of words through predictive text of the AI and not music composition with prerecorded loops. Writing a poem or a story or an essay also feels different than writing a song that layers words over music.

Even as I write that, though, I realize: that statement doesn’t seem to sit well with me at all — all are creative acts that begin with nothing but an idea and lead to something that others can experience. Maybe my conflicted feelings stem from being so used to technology being integrated so fully into the modern field of music production, and I am not yet used to its use in the field of writing.

Not yet, anyway. Will time and experience change that?

Garageband and Soundtrap and others don’t cite the musicians where the original loops came from. Do we expect that ChatGPT and others will cite where their words come scraped from? I believe that to be a strong yes in my view – that such information about original sources should be baked into the chart system (even as I understand the technical aspects will make such a thing nearly impossible). If this were done, then a writer could cite the sources of their AI-influenced writing.

Right? Hmm.

How confusing is all this? Pretty.

And how interesting to grapple with it? Very much so.

Peace (in the machine),
Kevin

Assorted Poems

Wrought Iron Words

These poems were mostly written each morning via Mastodon, with a one word prompt to guide the writing. I compose them quickly, so quality varies. If the poem has legs, I work to enhance them with a visual.
Hanging On
Brave Against the Weather
Words Erased
All That Is Wonder
Frost Blanket

Peace (and poems),
Kevin

Book Review: The Cartographers

 

Novelist Peng Shepherd pulls a nice trick with her book – The Cartographers — in that she maintains elements of mystery and surprise in a book that has a single old map at the center of the story. Even as a lover of maps, I didn’t think a single map could fuel an entire story. But here, it does.

And I won’t give the story away, but The Cartographers is an engaging tale that begins with a suspicious death, the discovery of an old road map with an odd marking, and a threading of a deep backstory into the present, all the while keeping a focus on Nell, the main character at the heart of the story. Nell’s father’s death is the event that sparks the tale, but it is also her search for her mother, or a memory of her mother, that propels the plot.

There are plenty of twists and turns, and the writing keeps it all moving forward. Focusing in on a collection of characters with a love of maps — from the old, dusty troves of ancient maps to a modern, algorithmic software program — Shepherd allows us to see how powerful maps can be on our imagination, and our perceptions of reality (or misperceptions, too).

It would give the main story away to share Peng Shepherd’s Author’s Notes at the end of the book, but the story she tells there of a real event that inspired her thinking about this fictional story is really quite fascinating — it’s a story of a map that signaled one thing, only to lead to something else altogether, where the map became a path forward in a place that was never real, until it was.

The Cartographers was a fun, lively read.

Peace (off the edge),
Kevin

From Song To Poem: Slow Walking Through Sleep

I was working on a song the other day, started early after a restless night (not all that unusual for me), and needed a title. I came up with Slow Walking Through Sleep, and as I was pulling the music beneath an image, words to a poem began to filter in. So I added that, too. I debated about whether I should add my voice, reading the poem, but opted against it, to allow the music that started it all to shimmer through.

Peace (and Song),
Kevin

Reflecting On ChatGPT And The Teaching Of Writing

Chalk Talk ChatGPT Daily Hampshire Gazette

Like many educators, the arrival of ChatGPT has raised some of my alarm bells and also piqued my interest. I wrote about this, from a teaching perspective, for the local newspaper. Interestingly, it was written a few weeks ago, and even now, I find there are more wrinkles with the topic that could have made the piece better. Oh well.

Peace (with the Bots),
Kevin

Movies On The Page: Internet Archive Remix

My DS106 friend, Paul B, shared a call from the Internet Archive, inviting people to use material from 1927 — now entering the Public Domain — for creative remix for a contest with cash awards. I sent the invite along to two of my sons who are filmmakers and then thought, What about me? (And what about you? See the Internet Archive blog post with all the information)

I dove in and came up with idea of using a 1927 periodical’s front page as a series of movie screens for clips from animated movies from the 1927 collection. I was hoping for something more narrative cohesive, but I ran out of time and patience and technical know-how.

I still like how the project came out, though, with little screens on the page, and clips from the movies showing. And the other entries coming into the contest are pretty cool. Check out the page where the projects are tagged.

Peace (and remix),
Kevin