Maximalism? What is the Genre for Hiromi?

It sure ain’t minimalism.

The Sonicbloom band:

The Trio Project.

1 Like

It is if the trio project is just three musicians! I like her stuff, I’d love to see her live.

Hi @AndersVinberg,

in her concerts Hiromi calls this kind of music “Fusion”. I’ve seen her live four times. A great pianist!

Jazz / Modern Creative / Post Bop / Fusion is where I would put her, but those are all pretty broad.

I’m not sure genre is the right way to cut it up for her, though. Her harmonic language is very much from modern jazz. It’s the energy level/mood that really differentiates it from most of the rest of the genre.

A lot of the music that I think of as related is in totally different genres.

I would love to do some kind of audio-based vector space search to find stuff that has similar perceptual qualities.

It would be good to get some systemic thought into this problem.
The assigned Genres are pretty meaningless — I totally ignore them.
“Maximalism” was a joke, both a comment on her fire and on the meaningless “minimalism” which covers The Necks and Argo Pärt.

And “fusion”, as @HWZ mentions, is also meaningless. Fusion 9f two things — which two? Tom Waits and Olivier Messiaen?

Although applying math and AI to such a humanistic problem is not easy.

The field gets a fair amount of research attention. There is a lot of prior art for extracting mood/genre information and determining audio-based similarity. At this point, the most widely used mood and genre databases out there were generated by CNN’s, not humans.

The whole tradition around classifying music via genres is a mostly irredeemable mess. Genres vary widely in granularity and meaning. Different people have different strongly held convictions about how it should work that are often self-contradictory. Even in official, maintained genre systems, genres are overloaded to represent other concepts. Bebop is a pretty well-understood/defined thing, but String Quartet should be a form. Then there is InternationalFusion could mean many things, but is usually understood in a particular way.

The goal of a machine learning system doesn’t have to be “better human visible labels”. That may not even be a problem worth solving–humans may have already proven that getting everyone to agree on labels is futile, and practicality dictates that most people aren’t willing to laboriously design and implement their own labeling system for themselves.

But–clustering or relating items without labeling the relationships is likely a lot more tractable.

Anyways, the main point I want to make is a little bit of a tangent, but interesting with respect to your “humanistic” comment.

There’s an interesting shift going on in how machine learning systems are operating. We started with big collective systems like pagerank or collaborative filtering, where the whole world shares one model. When things appear personalized, it is just personal queries or simple filtering of the shared model.

This is changing. Machine learning systems are starting to adopt a split model where the models themselves are trained on a user by user basis. This is happening for the usual boring reason: computing power continues to get cheaper.

In this scheme there’s usually an expensive centralized training step that is shared, and then the model is duplicated for each user and refined based on data that came from that user (often these models then do their inference work on the user’s hardware). So this is still a bit of a hybrid approach. At some point, it will be practical to centralize it again.

The benefit of this sort of approach is that it brings it closer to the user who is experiencing the results. We don’t have to come up with a model that everyone agrees on–the model can learn the objective parts generically and the subjective parts in context of one user’s experience.

1 Like

Yes, it’s very interesting.

One observation about the new world:

We are good at working with problems with a few parts, a thousand parts, maybe a million parts and relationships. That’s why we can build motors and bridges and skyscrapers; the space shuttle is order one million parts, and it’s right at the ragged edge of engineering. This is Newton’s world.

We are also good at dealing with a trillion trillion parts. This is Avogadro’s number, the number of molecules in a glass of water. We obviously can’t calculate what every molecule does, but we don’t have to, we can use statistics, the average speed of the molecules translates to the temperature. This is thermodynamics, this is why we have electricity and lighting and paint.

But midway between those two domains, when we have a trillion things, we have all those fields that do not work: economics and politics and medicine and psychology. These are arguably the most important fields for humanity, and they don’t work.

I think the biggest impact of the new technologies will be to revolutionize these domains.

High-falutin’ talk. What does this have to do with music and genres and personalization? Spotify has tens of millions of albums, and tens of millions of users, right? That’s roughly a trillion relationships.