I often want to search also by semantics of lyrics not only beat. I think there should be option for both.
EDIT: doesn't work for https://maroofy.com/songs/1640070887
Show HN: I trained an AI model on 120M+ songs from iTunes
351–360 of 444 posts
Re: Show HN: I trained an AI model on 120M+ songs from iTunes
#352I'm wondering if anyone has done something similar, but instead of trying to find similarities in the raw audio, they use tags available from sources like Last.FM, Musicbrainz, Discogs etc? And the ultimate answer to that is probably "those sources kinda suck". Discogs is like a trainspotter on the spectrum, fascinated by release IDs. Musicbrainz is kinda similar (each song will have a dozen matches of wildly differe…
I've tried with Discogs and found it to work pretty well. Kinda similar to what OP did just the "embedding" vectors was created by the Genre/Styles on Discogs. I didn't have a Vector database though, so it was kinda very slow. On Discogs those tags are per album and not per track. To create a playlist of say 10 songs similar to a song, I'd find the ten closest albums, then search for them on last.fm and pick the most popular track on each to add to the playlist.
Re: Show HN: I trained an AI model on 120M+ songs from iTunes
#353Earlier quoted context omitted.
Yes. I think many of those features are based on pre-NN feature detectors (such as BPM), and Danceability, Valence and Energy sound like primary components that have been given names. Echo nest was great for its time, but if they have kept up, they're not exposing their more modern learned features to users anymore.
They were acquired by Spotify, and there's been some work done by/for Spotify since then. I'm not at liberty to say what, sadly, as I work for Spotify. I think I can say that one of the main challenges is running this analysis for users. It's prohibitively expensive (or was prohibitively expensive) to use this to keep track of and run recommendations for what users are listening for each user. It can be used on small…
A distributed, local-first architecture much work well for this. I’m happy for my computer to crunch away on my behalf, generating recommendations and indexing stuff. I’m happy to recontribute that work to a common index of some kind.
I def prefer for that common index to have a permissive license though!
Re: Show HN: I trained an AI model on 120M+ songs from iTunes
#354Finding sources for input data is something I struggle with when building deep learning models. Out of curiosity, how did you go about programmatically accessing the music files for all 120M+ songs, in order to create your embedding vector? I can't imagine iTunes has an API which would let a person do that.
Also would like to know. I can't even listen to the full songs, and assuming I have to pay. I can't imagine buying 120 million songs, so it has to be some collab with iTunes.
Re: Show HN: I trained an AI model on 120M+ songs from iTunes
#355Earlier quoted context omitted.
Yes. I think many of those features are based on pre-NN feature detectors (such as BPM), and Danceability, Valence and Energy sound like primary components that have been given names. Echo nest was great for its time, but if they have kept up, they're not exposing their more modern learned features to users anymore.
They were acquired by Spotify, and there's been some work done by/for Spotify since then. I'm not at liberty to say what, sadly, as I work for Spotify. I think I can say that one of the main challenges is running this analysis for users. It's prohibitively expensive (or was prohibitively expensive) to use this to keep track of and run recommendations for what users are listening for each user. It can be used on small…
Can you say why Spotify's recommendations are so bad? Something like what OP has made should have been relatively simple to make for Spotify for many, many years already, yet that hasn't happen. Is the whole system just rigged to only recommended a few "sponspored" artists?
Re: Show HN: I trained an AI model on 120M+ songs from iTunes
#356I searched for "Poinciana" by Keith Jarrett[1] (one of my all-time favorites). The top three responses were "La Raya" by Los Islenos [2], "Days of Our Love" by Deepa Dremata [3], and "Flying Home" by Michelle Mack [4]. While I didn't hate any of them, and they all featured a piano, I wouldn't say any of them sound like Keith Jarrett, either. [1] https://music.apple.com/us/album/poinciana/1446740946?i=1446... [2] http…
I had similar experience
it doesn't seem to understand anything about the style of the music
seems to find stuff which is sonically similar rather than musically similar, and even then I'm being generous
no useful recommendations
Re: Show HN: I trained an AI model on 120M+ songs from iTunes
#357Finding sources for input data is something I struggle with when building deep learning models. Out of curiosity, how did you go about programmatically accessing the music files for all 120M+ songs, in order to create your embedding vector? I can't imagine iTunes has an API which would let a person do that.
Probably scraped them
Re: Show HN: I trained an AI model on 120M+ songs from iTunes
#358The homepage is an empty page with just one search box in the middle. It does not work in firefox.
Hmm I actually use Firefox myself, but tbh, it can be a bit flaky atm due to the sudden surge in traffic. Should become more reliable soon!
It works great, but I couldn't get it to work on Safari on iOS, have to click the "Listen on Apple Music" button to get any sound at all.
Re: Show HN: I trained an AI model on 120M+ songs from iTunes
#359Earlier quoted context omitted.
I agree with everyone's criticisms that it seems to identify similar tempo and melodic riff, irrespective of genre. But to me this is a feature, not a bug. I could see this or something like it opening my eyes to music I would never possibly have found on my own. I really like it! Spotify on the other hand seems to want to send me to the same group of artists and tracks I've listened to before, following some Collatz…
It’s a pretty cool idea and gets to a philosophical question really quick “what do people mean when they say they like similar music?” Era? Artist? Genre? Sound? Tempo? Personally I spend my time finding similar-era music because I like to hear how sounds evolved.
Ideally one would like an algorithm to be able to realize,"this person prefers to explore new music from the same era," vs "that person prefers to jump around to different countries," vs "the other person prefers to remix their existing playlists," and thus come up with the optimal degree of novelty for each listener. Or at least let the user set a novelty slider to customize their own experience.
Re: Show HN: I trained an AI model on 120M+ songs from iTunes
#360Finding sources for input data is something I struggle with when building deep learning models. Out of curiosity, how did you go about programmatically accessing the music files for all 120M+ songs, in order to create your embedding vector? I can't imagine iTunes has an API which would let a person do that.
Also would like to know. I can't even listen to the full songs, and assuming I have to pay. I can't imagine buying 120 million songs, so it has to be some collab with iTunes.
Thinking about both processing time and the difficulty of sustaining 120M downloads' worth of programmatic access, I wouldn't be surprised if this is actually trained on the track previews.