I love it. A kind of musical search engine for synaesthetes
The lie of music discovery algorithms
161–170 of 198 posts
Re: The lie of music discovery algorithms
#162Music discovery -- or discovery of movies, TV shows, love interests, or anything else that caters to human preferences -- is an enormously challenging problem that those whose business it supposedly is to solve have largely given up on. Part of the problem is exemplified in this thread: there are endless different ideas of what the ideal $ITEM discovery algorithm should do. Even if the Spotifys of the world were to deploy some modern AI-based tools to fix the problem, the level of tweaking each listener/watcher would need would be so extensive as to belie the entire effort. So they don't, for at least 2 reasons:
First, it's hard, as we all know.
Second, it turns out that the "best $ITEM discovery algorithm" accolade doesn't pull in that much extra revenue. It's far better (for them) to use people's expectations of such an algorithm to profit from a bait-and-switch. As an example, see Amazon's search engine.
Re: The lie of music discovery algorithms
#163Earlier quoted context omitted.
The “and still obsessively digs crates” was important I think. DJ’ are not even close to fungible (hell, I’ve even met a couple who don’t like music much) All music recommendation engines at this time still aspire to be mediocre, they aren’t even playing the S.A.,e game as a human who is good at it. Unfortunately, such humans are unevenly distributed.
My point is more about DJ specialization I guess. The vast majority of DJs I know personally still dig crates all the time - but they are techno/house/D&B/etc DJs, they know close to nothing about music outside of these genres. This goes so deep that some German techno DJs haven't even heard of Krautrock, the German scene that in many ways was a precursor of electronic music.
Huh. Ok - that really doesn’t match my experience , but that’s path dependence for you.
Re: The lie of music discovery algorithms
#164Even though the idea of recommendations is anything but new, literally nothing and nowhere works as expected. The only thing that comes close is based on the concept of neighbours, as implemented at Last.fm or RateYourMusic. I don't understand why is it so hard to offer something along these lines: 1. Define dominant user preferences by clustering and segmenting the field of listened genres. 2. Build a list of releva…
Confounding factors are
1. The curse of dimensionality when computong distance functions and
2. The cost function of a bad song. People get mad if they get too many things they don't like. Notice Pandora immediately sends you back to the band that seeded a station upon any thunbs down.
Re: The lie of music discovery algorithms
#165Like many people here, I've never found algorithmic recommendations useful. What works best is what has always worked best: recommendations from people with similar taste.
Back in the day, this was friends lending me CDs. Now, I follow a bunch of people on Mastodon who almost only post about music.
I've also found following the releases from specific smaller record labels quite useful - often the artists on a label will fit a certain vibe, even if they don't specifically overlap in genre.
Re: The lie of music discovery algorithms
#166I think I speak for most people when I say I want my music "discovery" playlist to be something like "mostly stuff that sounds like stuff I've indicated that I like" with a small amount of "not sure I'll like it, but suprise me". It sounds like OP is looking for the ability to turn up the "surprise me" factor at the expense of maybe having to skip a few more songs that just aren't clicking with them. So maybe somethi…
YouTube music actually has the ability to set how this works with its "radio" feature.
You can set the seed artists, then select levels for "artist variety" and "music discovery." You can also filter based on tags.
Re: The lie of music discovery algorithms
#167One of the things I find frustrating about music suggestions is that the app/algorithm doesn't care why you like a certain band. A long time ago I asked Pandora to make David Bowie station and it rolled me a generic classic rock station -- Zeppelin and the Stones. I was hoping for old school glam, maybe T-Rex and Eno. There's no way to communicate that desire to our music players. To say, "please don't think me a bas…
It seems some of these services (e.g. Spotify) don't really do musical similarity, but instead emphasize indirect "other fans also like" similarity. That tends to disregard many reasons you like a particular track, and does especially badly when the liked-track isn't part of a uniform style for an album or artist. I recognize it's a heck of a lot easier to implement, but it's still a disappointment.
They definitely do both, in the public recommendations API you can see vestiges of the old EchoNest acoustic properties along with some new ones they’ve come up with. It’s fun to play around with.
https://developer.spotify.com/documentation/web-api/referenc...
The guy behind Every Noise at Once (engineer at EchoNest/Spotify until the recent layoffs), has some interesting thoughts about this topic:
https://www.furia.com/page.cgi?type=log&id=478
He’s quite biased towards not using ML or acoustic characteristics for recommendations. But even if you disagree it is interesting to hear about how things were working under the curtain (for daylist in this case).
Re: The lie of music discovery algorithms
#168So I've been using Tidal for 5 years now, and feel they run circles around Spotify in terms of curation. Their algorithms and curated tracks are better, and they steer away from the social/gamification features and lean in to artist-centric features. For example, they've had a "credits" feature since day one - you can look up the producer, guitarist, oboeist, etc of any song, and see what other work they've done. In…
Spotify has song credits too, just FYI. In my experience, and the reason I left Tidal several years ago, is that they lean heavily into modern hip-hop, compromising relevancy for the sake of promoting "friends of the company" (Jay-Z, Beyonce, etc).
Spotify only lets you read a very reduced version of the credits of a song, and you can't click on the artist to see all of their work. On Tidal, the credits are much more extensive, and you can go deep down the rabbit hole of a producers work in one click.
More importantly though, Spotify doesn't directly link artists to bands they're in. For example, on Spotify, Billie Joe Armstrong is credited with his work on Green Day, but if you go to the Billie Joe Armstrong page, he isn't. On Tidal, each artist can also be broken down by their role on a project. For example, you can see just the songs that Paul McCartney wrote (turns out he wrote a track for Drake called Champagne Poetry in 2021... who knew). On Paul McCartney's page on Spotify he isn't even attributed to The Beatles
Re: The lie of music discovery algorithms
#169So I've been using Tidal for 5 years now, and feel they run circles around Spotify in terms of curation. Their algorithms and curated tracks are better, and they steer away from the social/gamification features and lean in to artist-centric features. For example, they've had a "credits" feature since day one - you can look up the producer, guitarist, oboeist, etc of any song, and see what other work they've done. In…
I would naively assume that both Spotify and Tidal pull that information from the same sources. Hopefully there is a web service. Not to take anything away from the first person who decided to, you know, actually tell us this information. At this point it should be table stakes for a music streaming service-indeed, it should be a legal requirement if you ask me.
They 100% do not pull from the same sources.
Hey Jude by The Beatles - Tidal lists 22 different people who worked on this song. Spotify lists 3.
Re: The lie of music discovery algorithms
#170So I've been using Tidal for 5 years now, and feel they run circles around Spotify in terms of curation. Their algorithms and curated tracks are better, and they steer away from the social/gamification features and lean in to artist-centric features. For example, they've had a "credits" feature since day one - you can look up the producer, guitarist, oboeist, etc of any song, and see what other work they've done. In…
Oboeist? That is oddly specific. Why that example?
Because it's completely obscure, and Tidal lists all of the obscure people who work on the songs. Spotify does not.