>Why is establishing genre a goal in the first place?
What is culture, if not a common agreement on what is beautiful and ugly? Establishing a genre in music is not a goal, but we see it happen over and over again. It is how humans operate since forever, we mimic one another in fashion, in music and many other things.
> Genre is defined by critical consensus, and it can arise around one or a handful of bands.
It arises around a handful of bands, but if it doesn't grow past 5 bands let's say, we are talking about 50 songs in total every year. Who listens nowadays to only 50 songs per year?
> And if the genre doesn’t have a significant recorded catalog, you can’t train a generative AI to produce it anyway.
Yes you can. Synthetic data generation is a big thing already and tens of millions of dollars are poured into it every year.
I’m not sure if you misunderstand genre, or the way humans relate to music, or both? Culture is not genre. I don’t know anyone who listens to only the current year’s output from a single genre.
I haven’t done the analysis, but consider someone who listens to pop radio: if one new song per week makes it into heavy rotation I’d say that sounds like the right ballpark.
Personally I’d be ecstatic if there were 50 worthwhile new songs to listen to each year.
I understand synthetic data. I question whether anyone will accept the results.
What is culture, if not a common agreement on what is beautiful and ugly? Establishing a genre in music is not a goal, but we see it happen over and over again. It is how humans operate since forever, we mimic one another in fashion, in music and many other things.
> Genre is defined by critical consensus, and it can arise around one or a handful of bands.
It arises around a handful of bands, but if it doesn't grow past 5 bands let's say, we are talking about 50 songs in total every year. Who listens nowadays to only 50 songs per year?
> And if the genre doesn’t have a significant recorded catalog, you can’t train a generative AI to produce it anyway.
Yes you can. Synthetic data generation is a big thing already and tens of millions of dollars are poured into it every year.