Generating music with expressive timing and dynamics • Hacker News Board

Re: Generating music with expressive timing and dynamics

#21

Post by iansimon » Fri, Jun 30, 2017, 4:19 PM UTC

kastnerkyle wrote: post #3

This is stunning! Great stuff. Since the input and prediction is a single sequence, did you experiment with beamsearch/stochastic beamsearch decoding (maybe with additional diversity criteria)? I found that even simple models (markov chains) got a big diversity boost with a stochastic beamsearch - it might avoid the problems with low temperature repetition that could happen in a standard beamsearch. However, my music…

Hey Kyle, we didn't try anything more advanced than next-step sampling. You probably have a better sense than I do how much improvement such techniques are likely to yield. My unfounded suspicion is that we're close to the limit of generation quality from this dataset, and so I'm most interested in trying to gather 10-100x more skilled performances, one way or another.

There's also no consensus on whether the high- or low-temperature samples sound better. I've heard both opinions from several people.

Sageev did the final rendering, not sure what he used but I'm pretty sure it was nothing too fancy.

Re: Generating music with expressive timing and dynamics

#22

Post by divenorth » Fri, Jun 30, 2017, 7:01 PM UTC

3131s wrote: post #12

divenorth wrote: post #10

Earlier quoted context omitted.

I'm passionate about this subject so here's my take on it. Until neural networks can create music better than humans it will be nothing more than table talk. Usually for something to gain any real traction it needs to solve a problem or do it better than current solutions. AI generated music does neither. From a music nerd who loves programming and neural networks I find this stuff very interesting. But I feel that n…

Yeah, I make electronic music and I'm really interested in algorithmic techniques as an aid to the composer too. I have python scripts that just generate many minutes worth of music in an instant, and then I comb through the result and cut out the interesting parts for further processing. It's a really productive technique and you hit on melodies and rhythms that normally a human wouldn't.

If AI is used as a tool to help composers become more productive it would be a massive hit. The ability to create new interesting stuff in less time is valuable.

Re: Generating music with expressive timing and dynamics

#23

Post by kastnerkyle » Sat, Jul 01, 2017, 6:16 PM UTC

iansimon wrote: post #21

kastnerkyle wrote: post #3

This is stunning! Great stuff. Since the input and prediction is a single sequence, did you experiment with beamsearch/stochastic beamsearch decoding (maybe with additional diversity criteria)? I found that even simple models (markov chains) got a big diversity boost with a stochastic beamsearch - it might avoid the problems with low temperature repetition that could happen in a standard beamsearch. However, my music…

Hey Kyle, we didn't try anything more advanced than next-step sampling. You probably have a better sense than I do how much improvement such techniques are likely to yield. My unfounded suspicion is that we're close to the limit of generation quality from this dataset, and so I'm most interested in trying to gather 10-100x more skilled performances, one way or another. There's also no consensus on whether the high- o…

A bigger dataset of MIDI with velocity information and performance timing would be really, really great.

High temperature versus low is tough to compare - I find that sometimes low temperature seems better, then I change the random seed and my opinion flips.

Same for stochastic versus deterministic beam search, length/diversity scoring, and so on. I have been meaning to blog on this, will send it your way when I get it posted.

For character text, stochastic seems nicer broadly (maybe due to limited size of markov space, see [0] deterministic vs. [1] stochastic) but for music it depends on the representation I use. However at least in this cherrypicked example, I find the repetition of the deterministic beamsearch hilarious even though it is "worse".

Interesting, I will have to ask him what it was. With that render, at least my bad samples will sound prettier.

Great job on the model again!

[0] https://badsamples.tumblr.com/post/160767248407/a-markov-arg...

[1] https://badsamples.tumblr.com/post/160777871547/stochastic-s...