I'm working on an IDE for music composition. http://ngrid.io Launching soon. Music is fundamentally unsolvable by AI. We'll have AI writing code before we'll have AI writing meaningful music.
Error 500 for me on Firefox as well
Jukebox
31–40 of 134 posts
Re: Jukebox
#32I'm working on an IDE for music composition. http://ngrid.io Launching soon. Music is fundamentally unsolvable by AI. We'll have AI writing code before we'll have AI writing meaningful music.
Error 500 for me on Firefox as well
Refresh a couple of times. Idk why its happening but I'll move to a new hosting soon.
Edit: seems to be fixed now?
Re: Jukebox
#33Can anybody explain why the researchers are attempting to generate the whole song as a single waveform, as opposed to wiring generated MIDI into some instruments and separately a singing algorithm (perhaps a bit easier than the whole bulk work)?
It's very hard to express all the nuances of real music and tonality in MIDI -- so generating raw audio side-steps all the limitations of a MIDI intermediary, and IMO, the results are absolutely phenomenal!
(BTW, there are lots of AI music generators that generate MIDI, so it's less interesting either way.)
Re: Jukebox
#34Personally, I think the example "songs" are all awful. None of them would succeed on any criteria, despite the admittedly low bar for music composition and vocal performance that passes today.
This project only serves to demonstrate that computers cannot make art; only people.
Re: Jukebox
#35Oh wow, well at least Skynet has decent taste.
Re: Jukebox
#36Can anybody explain why the researchers are attempting to generate the whole song as a single waveform, as opposed to wiring generated MIDI into some instruments and separately a singing algorithm (perhaps a bit easier than the whole bulk work)?
Well it’s not midi but what you’re describing is similar to this approach:
Re: Jukebox
#37"the top-level prior has 5 billion parameters and is trained on 512 V100s for 4 weeks" If they used on-demand AWS instances, it would cost about 1,342,623 USD to train the top-level prior. So much for reproducing this work.
My only question with OpenAI is whether they will forever-more take existing AI research, throw $100,000s of dollars at it in training, then take credit for inventing intelligence
I mean if they’re properly citing their sources I think it’s useful to have someone throw lots of compute at things and see what happens.
Re: Jukebox
#38Can anybody explain why the researchers are attempting to generate the whole song as a single waveform, as opposed to wiring generated MIDI into some instruments and separately a singing algorithm (perhaps a bit easier than the whole bulk work)?
We did work last year on MIDI alone - https://openai.com/blog/musenet/ and some early work now on conditioning the raw audio based on MIDI (early results at the bottom of the Jukebox blog). Agreed though there should be interesting results from modeling different blends of MIDI, stem, and raw audio data. Raw audio alone gives us the most flexibility in terms of the kinds of sounds we can create, but it's also the most challenging to get good long term structure. Still lots more work to be done!
Re: Jukebox
#39now generate thousands of fake albums, upload into spotify and collect royalties.
Re: Jukebox
#40https://jukebox.openai.com/?song=787730953
You got me good