devinroth
commented
5 years ago This is a topic I’ve spent lots of time thinking about. This paper is definitely a step in the right direction in terms of generating convincing audio. As a composer the music aspect sounds like random audio clips of a short duration being edited together. A NN remix. And knowing how the code works it is exactly that.
I think another algorithm should be used to generate the notes and something like this to generate the audio.
I’m excited about the developments in this field.
On Jul 29, 2018, at 12:19 PM, Benimation notifications@github.com wrote:
Is anyone maybe aware of an implementation of this paper? https://arxiv.org/pdf/1806.10474.pdf
It seems to rely on much of the same stuff, except now it has the ability to generate sort of consistent music over long periods of time.
Here are some samples of piano music they generated: https://drive.google.com/drive/folders/1fvS-DU8AcK078-5k6WGudiBn0XSeE0_D
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or mute the thread.
Is anyone maybe aware of an implementation of this paper? https://arxiv.org/pdf/1806.10474.pdf
It seems to rely on much of the same stuff, except now it has the ability to generate sort of consistent music over long periods of time.
Here are some samples of piano music they generated: https://drive.google.com/drive/folders/1fvS-DU8AcK078-5k6WGudiBn0XSeE0_D