41–50 of 189 posts
This may be academically interesting, but the music still sounds fake enough to be unpleasant (i.e. there's no way I'd spend any time listening to this voluntarily).
Most previous attempts at neural net composition restricted the training set to one style of music or even one composer, which is pretty silly if you understand how neural nets work. It was obvious to me if you used a very large network, chose the right input representation, and most importantly used a complete dataset of all available music, you would get great results. That's exactly what OpenAI has done here.
It is still lacking some longer term structure in the music it generates (e.g. ABA form). But I think simply scaling up further (model and dataset size both) could fix that without any breakthroughs. This seems to be OpenAI's bread and butter now: taking existing techniques and scaling them up with a few tweaks. (To be clear, I don't mean to minimize what they've done at all. "Simply" scaling up is not so simple in reality.)
What might still need some breakthroughs is applying the same technique to raw audio instead of MIDI. Perhaps what is needed is a more expressive symbolic representation than MIDI. I'm imagining an architecture with three parts: a transcription network to produce a symbolic representation (perhaps embedding vectors instead of MIDI), something like this MuseNet for the middle, and a synthesis network to translate back to raw audio. This would be analogous to gluing together a speech recognizer, text processing network, and a speech synthesizer. Such a system could generate much more natural sounding music, even perhaps with lyrics.
Something I'm curious about: If I make some music I really like through this tool, do I own the copyright to that? Can I turn generated music into an album and sell it? I'm not sure if the site does caching but if it does and me and another person generate the same music, do we both own rights to that?
If I look at the Marvin Gaye Blurred Lines case: https://en.wikipedia.org/wiki/Blurred_Lines#Marvin_Gaye_laws... that took years to resolve involving humans, I wouldn't personally risk to release machine-generated music that was trained on copyrighted music.
This seems incredibly applicable to musical scores in movies. I can imagine a product where the editor/director/someone inputs a handful of variables (mood, genre, instruments, etc) and timing requests (crescendo beginning at 30s and ending at 75s, calm period from 90s - 120s, etc) and out comes a musical score for the movie that matches up with their scene editing.
[1] https://filmstro.com/ [2] https://news.ycombinator.com/item?id=17132462
Something I'm curious about: If I make some music I really like through this tool, do I own the copyright to that? Can I turn generated music into an album and sell it? I'm not sure if the site does caching but if it does and me and another person generate the same music, do we both own rights to that?
The legal consensus, such as it is, seems to be that (if you did not otherwise agree to a contract/license modifying this in arbitrary ways) you create a new copyright & own it if you use their music-editing tool to tweak settings until you got something you liked, because you are exercising creative control, making choices, and engaging in labor. On the other hand, if you merely generated a random sample, neither you nor anyone else own a copyright on it.
Have anyone attempted to make a code autocomplete or snippet/boilerplate generator using this !? Would be nice when coding on mobile where its hard to navigate between code and navigation due to the small screen.
Jukedeck has significantly better AI generated music but since I have not found a description of how their model works, it is hard to compare it to this.
* Who uses piano as the lead instrument in bluegrass?
* They're only using one one note velocity for the whole piece, which misses a huge wealth of variation through rhythmic accent.
* Timing generally feels a bit robotic?
* The best parts it sounds kind of ok but boring; in bad parts it sounds like nothing (https://soundcloud.com/openai_audio/gaga-beatles is even worse that way)
* A lot of the artificiality seems to be the synth they're using.
* On the other hand it does understand a bit about phrasing and repetition, which many people new to traditional music take a long time to pick up.
This seems incredibly applicable to musical scores in movies. I can imagine a product where the editor/director/someone inputs a handful of variables (mood, genre, instruments, etc) and timing requests (crescendo beginning at 30s and ending at 75s, calm period from 90s - 120s, etc) and out comes a musical score for the movie that matches up with their scene editing.
Maybe more interesting for video games, where you can have a realtime input of gameplay variables.
Every gameplay a different soundtrack. Sounds fun.