Music: Melody Meets Motion

I’m working on a music compositional project of “small songs” and am about 14 songs in. These are pieces less than 2 minutes long. Yesterday, I finished this one, with a guitar focus.

Peace (with six strings or more),
Kevin

Saturday Morning: Poems and Music

Exceptional Sounds

A few things emerging from a creative Saturday morning … the poem above is from a one-word prompt (“exceptional”); the comic poem comes from Grant Snyder’s Comic Poetry Month daily prompts (“messy”); and the music track was something I tinkered with, liked and completed, and the title (“In An Otherwise Odd World”) was strange enough to generate an interesting image via Adobe Firefly.

Words in Motion comic poem

Peace (making it),
Kevin

The Beatles Final Collaboration (Thanks To Machine Learning)

I remembering reading something about Paul McCartney saying there was one more Beatles song under production, now that the Age of Artificial Intelligence was here, and to be frank, I thought: oh no. Please don’t let it be John Lennon AI Voice singing in the mix. Please don’t let it be AI George Harrison guitar.

It isn’t.

Instead, as I learned when I watched this short documentary last night, it’s a song that Paul, Ringo and George tried to work on decades ago to honor Lennon, with permission of his family, but the rough tracks that Lennon had recorded for a song that he never finished were distorted with loud piano and soft voice.

They gave up in the early 1990s. But now that Machine Learning is here and film director Peter Jackson has the technical skills, Paul realized, the computer algorithms and power could isolate Lennon’s voice and separate it from the rough mix that Lennon had made, and once the voice was isolated, they could build a song around it.

Harrison passed away in the meantime, so along with Lennon’s voice, Harrison’s slide guitar leads were also added into the recording, with McCartney and Ringo Starr playing along, allowing the claim that this is the Last Beatles’ Song to be true, such as it goes.

The song gets released today (Nov2), I believe. The documentary is worth a look.

Peace (and Sound),
Kevin

Music: Rhythms and Rivers

I was tinkering around with loops yesterday and began to imagine a river as I was working on this piece. Thus, the title — Rhythms And Rivers — and the image, generated by Adobe Firefly AI.

Peace (and sound),
Kevin

In The Test Kitchen With AI (MusicLM)

 

I got invited into the AI Test Kitchen by Google to begin beta testing out some early versions of their AI apps. The only one I saw available to me at this point in time was MusicLM, which was fine since I am curious about how text might be transformed into music by AI. (I’ve done some various explorations around AI and music lately. See here and here).

MusicLM was simple to use — write a text describing a kind of music (instrument, style, etc.) and you can add things like a mood or atmosphere and it kicks out two sample tracks, with an invitation to choose the best one. This is a trial version of the app and testing platform, so Google is learning from people like me using it. I suspect it may eventually be of use to video makers seeking short musical interlude snippets (but I worry it will put musicians and composers out of work).

I tried out a few prompts. Some were fine, capturing something close to what I might have expected from an AI sound generator. Some were pretty bad, choppy to the point you could almost hear the music samples being stitched together to make the file. Like I said, it’s learning.

The site does let you download your file, so I grabbed a file and took a screenshot and created the media piece above (here is direct link). My prompt here was: “Electronic keys over minor chords.” (An earlier prompt — a solo saxophone — gave me a pretty strange mix and I think I heard some Charlie Parker in there.

Here is what the Google folks write about what they are up to with MusicLM:

We introduce MusicLM, a model generating high-fidelity music from text descriptions such asĀ “a calming violin melody backed by a distorted guitar riff”. MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and it generates music at 24 kHz that remains consistent over several minutes. Our experiments show that MusicLM outperforms previous systems both in audio quality and adherence to the text description. Moreover, we demonstrate that MusicLM can be conditioned on both text and a melody in that it can transform whistled and hummed melodies according to the style described in a text caption.

I guess Google will be adding new AI-engined apps into the kitchen for testing. I’ll be curious.

Peace (and Sound),
Kevin

Slice of Life: Piano Crates And Imagination Rhythm

I’ve had time on my hands this past week and so I’ve wandered into making a few tracks of music. Here are two songs from yesterday, each capturing a little different emotional spin from being stuck temporarily at home. (Note: I think the songs are best experienced in headphones.)

 

Piano Crates (link)

 

Imagination Rhythm (link)

Peace (Rhythm and Sound),
Kevin