Library Music Themes
General Sharing & Discussion => General Discussion => Topic started by: moodmusic on January 18, 2023, 08:20:03 PM
-
I've been involved with emerging AI audio technology. For those not up to speed, here's what it can do.
James Brown - Escap-ism - Vocals
https://mega.nz/file/6NpwSSLa#c_s5OgpyNlMWMVhk32rFA4UabRF10qyDwAJxskvchQY
The difference with this AI model from what's publicly out there, is the quality level. Yeah, record labels are very worried about it.
-
I’m a fan of these Stem rippers and use Izoptope ‘Music Rebalance’ and have stripped a few library tracks back. Great sampling potential and just fun to mess around with.
-
I believe this tech is being used alongside Apple Music for its ‘Sing’ section of music in their libraries. Essentially within the music app, it offers the user the choice of reducing the volume of the lyrics so you can sing along to the song. Similar to how Izotope works I believe. Clever stuff !
-
I did a comp of some random tracks I’d stripped the vocal out of a while back: retroteque.wordpress.com/2021/05/01/no-words-1-instrumentals/
-
Izoptope is ok, but very fragmented. The AI model I'm working with is far more impressive at conversions because it's trained on more music. I run the code so I can do batch conversions of entire albums easily.
This is still the 1st generation of AI audio. Give it two years and it will be master quality. It will even restore audio, similar to how old black and white images/videos are restored to HD.
Some more...
David Axelrod - The Edge - Instruments
https://mega.nz/file/qQJDVKpT#mainkm3Ktof1o6ddiam2-hZ0ou4MszQOtuZG5ouZmy8
Gil Scott Heron - We Almost Lost Detroit - Drums
https://mega.nz/file/KIpnRKib#6NCOtExZjRX2ICe0T0ZiRMwk8A23gYXR21O47dmGxp0
-
I get an error trying to open the links
-
I've been involved with emerging AI audio technology.
... record labels are very worried about it.
Why are they worried? What exactly do you mean by "AI" in this context?
-
Because of my oriental connection I've been into karaoke for more than 40 years now. But I'd always been disappointed with the quality and standard of the average karaoke backing track. I've spent many hours with SoundForge, Audacity and other audio apps trying to isolate the vocal from the rest of the track but without success. I remember back in the early 90s having a Sony CD player that used a simple algorithm for cancelling out the vocals at the push of a button but only if the vocal was dead centre. But this is something else entirely since I take it you can isolate more than just the vocals? I'd love to know more though sadly, as with potzorbie, I get an error when trying to access the links.
-
Don't have a clue what AI is but is certainly not "Vintage Library vinyl and CD rips".
Moved to "General Discussion".
-
I did a comp of some random tracks I’d stripped the vocal out of a while back: retroteque.wordpress.com/2021/05/01/no-words-1-instrumentals/
Ah so that's how you produced the instrumentals. I thought they were genuine backing tracks that you had somehow managed to get hold of. I've really enjoyed listening and singing along to those tracks. But Izotope doesn't come cheap. Impressive.
-
@potzorbie Not sure. What's the best free site to share mp3s?
@likedeeler AI as in artificial intelligence for music. The labels are worried b/c this technology will devalue their masters. It's probably why they started offering their music catalogs for sampling on sites like Tracklib and Usample. They best make money while they can. Aside from stem separation, AI will be able to create songs on the fly. It's crazy.
@nidostar This is much different technology, not phase cancellation with vocals. If you want to try a song, post a link to the file and I'll separate it for you.
@Greta Sorry, I'm new here.
-
I've used AI to create stereo-ish mixes of a couple of KPM tracks that should be in stereo but aren't - I suspect the technology has improved since I did them, though, and it might be fun to have another go.
Is the system you're using a secret, moodmusic? I love trying stuff like this! I might put up a couple of tracks for you, if you don't mind
-
Welcome @moodmusic! This is a pretty exciting field indeed. I am always excited to read about AI, tho I care more about AI as a tool than AI as a creator, since I've followed progress on the latter and honestly didn't find anything worth looking at.
Wasn't able to access the samples you shared on file.
mega.nz is a good alternative I like to use.
-
I get an error trying to open the links
Yeah, none of those files are available. Best never to 'hotlink' the urls.
I'd love to hear these samples.
-
@stackjackson @Fuzi I fixed the links to MEGA.
@Lord Thames - It could be done with AI if the model was trained to do so. Mono to stereo is tricky. If you want a natural sounding stereo mix, the best way would be to mic up a pair of speakers in stereo. That's what Bruce Swedien did for Micheal Jackson's albums. He would take a mono signal for something like a Moog synth and play it off the studio room speakers — then record the speakers in stereo with a pair condensor mics. I've done it before. It works. But you need really good studio equipment.
It's no big secret. It's just pieces of code that data scientists are using for AI research. There's some paid services like AudioShake and Spleeter, and free code such as Open-Unmix, but they don't sound as good.
Although I should mention that the quality of the recording matters. From my batch runs I've noticed that anything recorded before the mid 70s doesn't convert well. Likely because they were recorded on 4-8 tracks with a low ips tape speed (more saturation noise). For 60s music 1-3 tracks. Anything from the late 70s onwards starts sounding really good, depending on how much instrumentation there is.
Post up some tracks. I'll run it on my next batch.
-
LT, on that subject did you ever get a good KPM 1044- Big Beat? I know the online wasn’t as good as the vinyl. Happy to do it if there isn’t a decent one about as o have mint LP.
-
Some more...
Cortex - Prélude à Go Round - Vocals
https://mega.nz/file/bQBCDAQC#h6AQVWFJlnxhqurwQuOb6yX96vQALu1mrJPEAU8h05E
Brian Bennett - Solstice - Drums
https://mega.nz/file/uI4RjDJQ#LCOic8MiEEfDIr0vkG5ORXNF6eJlYMuX93mSdi55Wms
Geoff Bastow - Beautiful People - Instruments
https://mega.nz/file/SBBWwBqB#Jj7N2AheEWeQmn-YohUeJziFnffIbuIpWVKRsGfBBC0
Piero Piccioni - Once and Again - Vocals
https://mega.nz/file/CZJwzbrK#RfFN0YsMm6Ok2__6jRfnewk9fdtznM6Jz1LfupVTgK8
I don't like calling them stems because it's not the actual multitrack from the masters. Only the record label has those. With AI technology the model makes predictions on what it thinks it would sound like if it were separated. It's more like a representation than a replicated copy.
-
LT, on that subject did you ever get a good KPM 1044- Big Beat? I know the online wasn’t as good as the vinyl. Happy to do it if there isn’t a decent one about as o have mint LP.
You sent me a rip of your vinyl ages ago, which I had a play with - Beat Me Till I'm Blue was noticeably less swooshy than the official KPM version, certainly
-
@Lord Thames - It could be done with AI if the model was trained to do so. Mono to stereo is tricky. If you want a natural sounding stereo mix, the best way would be to mic up a pair of speakers in stereo. That's what Bruce Swedien did for Micheal Jackson's albums. He would take a mono signal for something like a Moog synth and play it off the studio room speakers — then record the speakers in stereo with a pair condensor mics. I've done it before. It works. But you need really good studio equipment.
It's no big secret. It's just pieces of code that data scientists are using for AI research. There's some paid services like AudioShake and Spleeter, and free code such as Open-Unmix, but they don't sound as good.
Although I should mention that the quality of the recording matters. From my batch runs I've noticed that anything recorded before the mid 70s doesn't convert well. Likely because they were recorded on 4-8 tracks with a low ips tape speed (more saturation noise). For 60s music 1-3 tracks. Anything from the late 70s onwards starts sounding really good, depending on how much instrumentation there is.
Post up some tracks. I'll run it on my next batch.
Very interesting, thank you!
-
@stackjackson @Fuzi I fixed the links to MEGA.
Very cool! Thanks for re-posting these samples.
-
Interesting tool of IA as Izotope can do , but the result sound like an mp3 128kbps
some frequency are lost and confused
fortunately human can do it better ;)
for exemple here is Solstice with an open break isolated :
pixeldrain.com/u/ZynP5Wr2
-
As some of you may remember, I came here initially to gather together all the library music used in Doctor Who in the early days. I was soon re-directed to another site where a group of guys have been doing this for some years & were way ahead of me.
Fast forward to last year & something web-based called x-minus became available. Long story short, it was now possible to upload rips of Doctor Who episodes & have x-minus remove the voices to create soundtracks of composed (not library) music that is as yet unreleased or even lost forever & therefore unreleasable.
The results are far from perfect (in doesn't deal with sound effects at all well, as it can't seem to distinguish them from music) &, as far as I'm aware, it's only possible to save out the results in MP3 format, currently. Nevertheless, it's better than nothing & it can only get better, right?
-
@Sub I've been converting mp3 files as the source. That's all I have. A lossless format like flac or wav would sound much better, although the full frequency range still depends on the quality of the audio converter used to record it.
There's lots of rips out there, but many of these collections are recorded with poor audio converters at home. For the average listener it probably doesn't matter.
-
I have to say, there's some big opportunities right now for curators. Especially for drum breaks. AI audio separation is an Amen break killer with a plethora of isolated drums up for grabs.
-
... @likedeeler AI as in artificial intelligence for music. ...
"Artificial intelligence" is a marketing term. It has about as much to do with intelligence as L'Oréal's latest "facecream revolution" has to do with the French revolution. It's mostly used (a) by companies who have a bridge to sell you, and (b) by fanboys with little knowledge about the current techniques behind "AI" (essentially: "machine learning" -- another marketing term lacking substance), to impress people on the internet who have even less of a clue.
... The labels are worried b/c this technology will devalue their masters. ...
Who told you that story?
... It's probably why they started offering their music catalogs for sampling on sites like Tracklib and Usample. They best make money while they can. ...
They make money by offering their music for sampling. The reason being that they're a business.
... AI will be able to create songs on the fly. It's crazy....
The thing which is actually crazy here is your gullibility. Get rid of these overstrung notions.
You say that you've been involved with AI audio technology. What -- precisely -- do you mean by "involved"?
-
I've been involved with emerging AI audio technology. For those not up to speed, here's what it can do.
Cool - thanks for sharing! I've used Izotope and LaLaLa.ai over the past few years - success is very dependent on material, quality, and what I'm trying to isolate. And often, while the initial isolation may sound janky by itself, once I start layering other instruments and samples it seems to blend decently.
Looking forward to hearing more when the tech you're working with is available to the public. For sampling purposes, these tools open up huge possibilities!