Hacker News new | ask | show | jobs
by globalise83 821 days ago
I would describe myself as a good potential user of generative AI - I have an interest in electronic music, listen a lot, and like to play around with making simple tracks using LMMS and a MIDI keyboard. But have no background at all in music production.

What I'd be looking for is not generation of complete samples, but a tool that could coach me and assist me to achieve the sounds I am looking for with minimal technical know-how. For example, I might like to create a track with similar "instruments" to an existing track that I like. I could upload an mp3, the tool would identify the main "instruments", configure some kind of plugin for each of them, and then I could start making my own tracks using my keyboard and / or piano-roll. Eventually, I would graduate to making new "instruments", perhaps by generating variants of the ones that I have "favorited" in the past. Over time, I would become more adept at using the tools and interface available for tweaking the sounds.

2 comments

I use Melodyne to help me deconstruct music I like. Most recently in conjunction with various stem separation services.

Works well for me, but I have to say that I have a taste for minimalism, so the my starting point is already quite basic.

Yeah, I have a room full of synthesizers, each with their own unique features and engines and workflow.

What I really want is to be able to feed a sample to the AI and have it spit out SYSEX that will reproduce that sample on my room full of synthesizers, so that I can go from Sample->Synthesizable Sound, i.e. turn the static dead of a sample into a dynamic reproduction with hundreds of modifiable parameters.

I'm guessing someone is working on this. Aphex Twin had a cute project along these lines, but I dunno where it went ..

If you aren't familiar with it, Synplant 2 VST does an incredible "sample -> synth patch" for almost any sound you give it
Yes, that is indeed incredible - but I'd love to have the ability to upload an inventory of the synths in my room, and have the AI use any (or all!) of them for reproducing that sample.

I guess we're pretty close to that .. keep an ear out!

Do I understand you right, something like this: "go from sound sample to a bunch of MIDI, each MIDI tuned to each of your synthesizers, which will then reproduce the sample as faithfully as possible" ?

Something like that would indeed be very cool. Hope I understood you correctly.

Yes, exactly. The AI would analyze the sample and then re-create the patches based on the synthesizer engine, in use .. so for example, I give it a sample of a bell, and it goes ahead and reproduces that bell, as close as possible, on the Yamaha DX7 FM engine, meaning that I not only get a playable patch (not a sample, which is often dead-sounding) but can also then alter the parameters using the synth engine itself.

Like I said, Aphex Twin had a project like this a few years back:

https://fo.am/activities/midimutant/

.. but it ran into some limitations - I'd love to see this updated with modern AI techniques.