Every Noise at Once

Tried out a few prompts and the suggestions that came back didn't even seem in the ballpark of what I would've expected. Interesting idea nonetheless. https://everynoise.com/ is still my favourite for discovering new artists, especially in fairly esoteric genres.

> In the age of machine learning, I'm really surprised there aren't superhuman music recommendation algorithms. Because music is extremely hard to quantify. What do you quantify it on? See https://everynoise.com/ (the mess on the page is quantifying by just three or four out of 17 IIRC parameters) and their small doc on it: https://everynoise.com/EverynoiseIntro.pdf And doing that at scale across hundreds of millions of users quickly becomes prohibitively expensive. So companies simplify, and reach for simpler solutions, unfortunately.

Amazing! I wonder if the Every Noise At Once[1] site could be updated with the metadata from this? [1] https://everynoise.com/

Spotify has not viewed itself as a music company for longer than that. It's a platform for audio. And, while there are still music first people at the company, they are not in the power positions that they used to be. The transition didn't start when they laid off Glenn MacDonald, but that sort of cemented it. They had already gutted curation before that and by this time you were far more likely to find people talking about AI in the halls than music. If you've never heard of Glenn, check out his book: "You Have Not Heard Your Favorite Song: How Streaming Changes Music." Or his old online projects at https://everynoise.com/.

For what it's worth there is a phenomenal site that applies algorithmic matching not to songs but to genera classification and the branching sub generas that new song signatures introduce. An amazing resource run as a solo sidehussle and looks like it is at risk of getting clipped due to hosting issues or something. There was Music DNA from Pandora and something similar on LastFM back a long time ago but this site is like the visual connectome of all human music produced through to 2023 and would be a loss for the World Wide Web if it stops..... Every Noise At Once https://everynoise.com

The every noise at once site is also a great genre map I've sunk far too much time into: https://everynoise.com/

https://everynoise.com/ might be worth a look - start from an artist that you like and explore their genres

Because music is as messy as humans, and whatever we catalogue is arbitrary at best. See Every Noise: https://everynoise.com/ Is modern chamber music different from modern classical, and why? How different are Polish free jass and free imporvisation? Canadian black metal and Norwegian black metal and Dutch black metal? To some, there's no difference. To others, there's a world of difference. Here's more on the difficulties: https://everynoise.com/EverynoiseIntro.pdf

We're not likely to see one. DALL-E was trained by analyzing pixels along with the captions for images. It is the caption information which is used in understanding your prompts. But music doesn't have a form that ties the audio portion so cleanly to a textual description. And when it does, those labels tend to be overly simplified and not really helpful. Music is, in fact, hard to describe. One project that might interest you is Every Noise at Once[0], which does an amazing job of grouping known artists and songs by their sonic similarly, which results in similar style and listener appeal. [0] https://everynoise.com/

Worth mentioning is The Echo Nests old genremap; which is also very interesting to roam around in: https://everynoise.com/

https://everynoise.com Search for your favorite bands using the bar at the top right corner. Find the associated playlist on Spotify via "The Sound Of X" where X is the genre name. If you have (or would like to have) diverse musical tastes this is the best way to do it!

I use https://everynoise.com/ and randomly spam clicks until I hear a category worth exploring.

On the flip side SoundCloud, Spotify, Apple Music and websites like http://everynoise.com have made it even easier to find more obscure music, of which some is electrifying, change-your-life music. It doesn't follow that "more people making music" means "same amount of good music"

Gonna plug this site for music and genre datasets and recommendations. There's a treasure trove of data here if you go hunting. http://everynoise.com/

See also http://everynoise.com/ which is a view into how Spotify classifies music. The creator wrote about it here: http://blog.echonest.com/post/52385283599/how-we-understand-music-genr… and writes a lot about it on their blog: http://www.furia.com/page.cgi?terms=noise&type=search Of course those are going in the other direction, not generating the classification from the data, but it's probably one of the best data sets as far as classifying existing music.

The terms "sameness" and "average" are doing some heavy lifting here. In the grand internet tradition I will memetically unpackage "sameness" and "average" into four related components: (1) things that are BIG (2) things that are HOT (3) things that are COOL and (4) things that are GOOD. (1) things that are BIG — these are side effects of technological advancement, globalization, the Internet, and frictionless social media platforms. More people than ever before can book a TAP Air flight to Barcelona, stay in a budget AirBnB, and check Google Maps for the same "best cafe near me" that everyone else is going to. Access to the world and to information is more open than ever before, so more people have both the ability to congregate around the top N things (physically or virtually) and the means to do so. (2) things that are HOT — trends have always been around and always will be. Instagram face, the Kardashian look, hoverboards, heroin chic, microservices, Livestrong bracelets, putting "F*ck" in the name of your self-help book, flat icons, frozen yogurt, Dutch tulip mania — you can localize each one of these into a time period easily enough. Popular because they are new and a momentary cultural touchstone and different enough from the n-1th state of culture. (3) things that are COOL — what you might call "signaling theory effects". "Ads Don't Work That Way" [1] explains this in the advertising context better than I can, so go read that. Differs from (2) in that the cultural…

I sometimes wonder if we're looking in the wrong place with music recommendation systems. I've tried both Apple Music and Spotify; it's rare that I hear a song come through on the linear recommendation stream and think to myself "oh my gosh! that's exactly what I wanted!" For me, discovering new music is a branching experience, where I'm constantly listening to little bits of different things, figuring out what I like, and then looking online on forums and blogs to see what's similar to that. It's surprising that the company that owns YouTube, a platform driven by user choice and 'rabbit-hole discovery', would be looking for a new way to feed users linear song recommendations. I would much rather be able to see several 'similar songs' while listening to something, similar to YouTube's recommendation tab. Alas, no streaming service seems to have implemented this (not even YouTube music, afaik). https://cosine.club/ is the closest I've seen to the ideal branching system. My understanding is that it uses vector embeddings to search for songs that are similar in sound, and it works shockingly well for that purpose. However, it has a limited song database. Also see https://everynoise.com/, which is no longer updated. These use vector embeddings in similar ways, but the exploration experience is controlled by the user, not by a list-generating ranking model. I definitely think that AI-tech is the future of music recommendation, but I would prefer to see more research by large…

I mostly use playlists generated by this service https://everynoise.com/ (you can get to them with desktop client by pasting playlist links from the site to the spotify client search box.) From the site: "Every Noise at Once is an ongoing attempt at an algorithmically-generated, readability-adjusted scatter-plot of the musical genre-space, based on data tracked and analyzed for 5,646 genre-shaped distinctions by Spotify as of 2021-10-16. The calibration is fuzzy, but in general down is more organic, up is more mechanical and electric; left is denser and more atmospheric, right is spikier and bouncier." I personally think that an algorithm trying to learn my tastes and recommend music to me is the wrong approach... especially as the algorithm does not actually seem to care anything about the actual waveform content. I feel I get get this strange "personal echo chamber effect" where I at least think I notice the effect of my past listening habits or the outsized weight of some stuff that was on powerplay some time ago. It gets hard to find new stuff or to learn to like new stuff. This varies though, sometimes the recommendations are great. Perhaps they work best for me if I don't constantly follow or listen to them, but instead listen to playlists curated by humans or everynoise.com.

Has anyone made something like this for jazz, classical, or hip-hop? The closest I know of are: - https://www.music-map.com/ - https://everynoise.com/ - https://chartmetric.com/ - https://musicroamer.com/ - http://davidmckinney.com/app But they're all kind of generic, I would love to see something more genre-specific with additional historic context and personality.

Ya'll should checkout https://everynoise.com/. Similar in spirit. Just read the update: > 2024-01-05 status update: With my 2023-12-04 layoff from Spotify I lost the internal data-access required for ongoing updates to many parts of this site. Most of this, as a result, is now a static snapshot of what, for now, will be the final state from the site's 10-year history and evolution.. what a shame. I didn't realize the author worked for Spotify. Guess it makes sense. Spotify should've acquired it from the author or made a deal with him to keep it live since all the links lead to Spotify anyway.

Simply sharing metadata, related artists, genres, etc would create a pretty interesting ecosystem[1]. [1]: https://everynoise.com/

I'm hoping that this metadata leak can revive projects like https://everynoise.com Spotify (and netflix etc..) have become very hostile to exposing their catalogue over API, so i'm glad they've gotten open sourced :)

I'm surprised that https://everynoise.com still works, but it does. At one point, I had heard that it was shut down.

One of the gratest Spotify tools is : https://everynoise.com/#otherthings I hope they will long live

A map to me is something that organizes something spatially, two-dimensionally, like everynoise[1], which I don't really see here. [1]: https://everynoise.com/

I see this in https://everynoise.com/#updates > 2024-01-05 status update: With my layoff from Spotify on 2023-12-04, I lost the internal data-access required for ongoing updates to many parts of this site. Most of this, as a result, is now a static snapshot of what, for now, will be the final state from the site's 10-year history and evolution, hosted on my own server. Some pieces may get disabled and reenabled over time, and some that only made sense with current data may never return. But we'll see.

Anyone aware of a similar feature for foobar2000? I have an extensive library mostly tagged from Discogs, including release IDs. In theory, this should be sufficient to cluster music by genres, pull similar releases from Discogs "similar" feature and correlate data from https://everynoise.com. Obviously, in case of album mixed genres things will mix up, but I'm not sure there's a model that can correlate existing tracks with a genres/styles latent space which you can query for a playlist.

This is unfortunate. My favorite feature of EveryNoise is the geographic categorization of music genres: - https://everynoise.com/cities.html - https://everynoise.com/countries.html There are also features for "hyper local" discovery, i.e. finding the individual tracks that are most popular in your city. For music lovers, this site provides the initial breadcrumb for many fascinating rabbit holes. - https://everynoise.com/hyperspace_house_concerts.cgi

The article mentions Glenn McDonald's musical genre page (https://everynoise.com/, no longer refreshing with new Spotify data) as an example of a flexible graph-like exploration format, without being burdened by explicit connections. The author also has a thorough description of pros and cons of the general concept.

This is from Glenn McDonald's blog, founder of "Every Noise at Once". He was laid off from Spotify (discussed here briefly [0]) --- https://everynoise.com/ is now in "archival copy" mode [1][2]. Super sad to read / see this. [0] https://news.ycombinator.com/item?id=38650917 [1] https://everynoise.com/ [2] https://twitter.com/EveryNoise/status/1736086849339244935