Live data from Hacker News

MusicLM: Generating music from text

arxiv.org

41–50 of 114 posts

Re: MusicLM: Generating music from text

#42
post #18

I don't really understand why this approached is pushed for music. You can overpaint an image, but you can't do that with a song. Cutting an image to reintroduce coherence is easy too. For a song you need midi, or another symbolic representation. That was the approach of pop2piano (unfortunately it is limited to covers, not generating from scratch). And even if a song generated this is OK, listening to half an hour f…

I understand what you're saying, although it could be argued that at least for some types of image tasks one would prefer something like an SVG output with layers to make it easier to edit. For music, I think it's partly an academic question of "can we do it" rather than trying to maximize immediate practical usefulness. There's already quite a bit of work on symbolic music generation (mostly MIDI), a lot of it quite…

The difference is that for images almost everything is done with raster graphics, vector is the niche exception. And for most uses where it makes sense (e.g. a logo) you can easily convert a raster to SVG automatically generally without requiring any manual tweaking.

If the argument is that "maximize immediate practical usefulness" is not something interesting, I would say it makes sense to say "I don't understand why this approach is pushed". Anyway.

Re: MusicLM: Generating music from text

#44

I’m writing my second video game (old school arcade style side-shooter) and hope I can use this to generate background chip tune music!

I hope you also consider getting some music from an actual producer!

Why is there this need for humans to be involved at all stages of production?

Do we still need humans to knit and handwash our clothes? To live in a caboose or lighthouse? To operate our elevators? To deliver the milk?

Why should anyone have to learn to draw in the future when machines promise to do a better job? There are so many better uses for our time, and too many things to do for our short lives to handle.

I want to compose music, despite no practice or formal training. I want to make an entire movie by myself with no other humans involved. Tech that enables these things will be empowering.

Re: MusicLM: Generating music from text

#45
AI music is the next thing coming, wait for copyright lawsuits to fall like bombs.

I find it fascinating that MidJourney can make a 3D model of my face from a low quality image, rotate it in space, apply it on someone's else body, add coherent shadows and backgrounds, with a very credible result, and yet an AI cannot generate a decent song, which is 1-dimensional and has probably much less internal modelling to care about?

One reason I can think of is because eyes are "integrators" and ears are "derivators". That is, that human ear is very sensitive so small differences, whereas vision cares more about the ensemble? I don't know, but I think that AI music will come one day. It may not be as great as human music, but it will suffice for, say, putting a music background for your startup cheap marketing ad.

Re: MusicLM: Generating music from text

#46
post #32

Earlier quoted context omitted.

May I recommend to learn how to use a tracker software? It is very fun to play with!

what's a tracker software?

A 'tracker' is a usually-sample-based music making software. AFAIK they were originally developed by demoscene groups (concurrently to game studios that used the code privately whereas the demogroups would release binaries for others to use for music-making with few limitations) These 'sample mixing engines' were developed in order to be able to add music to their productions (demos and games), and it became it's own whole-world. Fully agree with sibling comments, module trackers can be huge fun! Near zero barriers-to-entry.. and there's still some great stuff being made in this format too!

Re: MusicLM: Generating music from text

#47
post #32

I’m writing my second video game (old school arcade style side-shooter) and hope I can use this to generate background chip tune music!

May I recommend to learn how to use a tracker software? It is very fun to play with!

yes, fits perfect for those kind of games

Re: MusicLM: Generating music from text

#48

AI music is the next thing coming, wait for copyright lawsuits to fall like bombs. I find it fascinating that MidJourney can make a 3D model of my face from a low quality image, rotate it in space, apply it on someone's else body, add coherent shadows and backgrounds, with a very credible result, and yet an AI cannot generate a decent song, which is 1-dimensional and has probably much less internal modelling to care…

Possibly just anecdotal evidence, but it seems like the pool of good music composers is much much smaller than the pool of good visual artists. Maybe that is an indicator of how "hard" each field is.

Re: MusicLM: Generating music from text

#50

Yet another cherry picked attempt at music gen with a "demo" page that only contains the outputs that happen to not sound like incoherent noise. There's a reason ChatGPT and Midjourney are so popular, but no music-gen tools have even come close: you can actually create stuff with them that is useful and/or enjoyable. Good music gen is much harder, and the reasons for this (still unclear) are pretty important to the f…

That's quite a harsh critique that doesn't seem warranted. There are quite a lot of different examples with varying quality. Granted, it's likely that these are to some extent cherry picked, but it's unlikely that these are rare and that most output sounds like incoherent noise, as you seem to insinuate.
Post reply on HN