Viewing profile — abdljasser2

code here: https://github.com/erl-j/neurosymbolic-music-generation

My plan is to become a people person / ideas guy.

Excellent post

Thank you! I can also recommend this work which had a similar idea: https://instrumentgen.netlify.app/

I made a soundfont generation AI to use in your productions I made this because I like the uncanny sound of Suno/UDIO but I want to use it in real time within my DAW. It’s free & n…

Good question. In my experience combining generic descriptors is what works best. This is probably due to the text captions used during training mostly consist of generic instrumen…

Generate soundfonts from text descriptions using latent flow matching. You can then download the complete SFZ soundfont package to use the instrument locally.

https://erl-j.github.io/textsynth/ Sortof ML, Evolutionary algorithm w/ fitness determined by a ML model.

[4] https://forum.juce.com/t/ddsp-tone-transfer-vst-possibility/...

[4] https://forum.juce.com/t/ddsp-tone-transfer-vst-possibility/...

Hello! I think this will be possible!

I can't say for sure but I think the issue with why the reverb sounds off in that particular example is that the reverb present in the recording has a longer decay than the maximum…

Thank you! Will do.

Very interesting! Thank you for this.

Very cool! Thank you for this. Speaking of wavetables, have you seen this relatively recent work? https://lamtharnhantrakul.github.io/diffwts.github.io/ ?

Hello! I think you accidentally mistook the first citation link for a link to the work we are presenting. Here is the link I think you are looking for: https://erlj.notion.site/Neu…

Great question! I think this approach (and DDSP more generally) could work well for most instruments if you make some adjustments to the synthesis architecture. The current archite…

Hello! I think this can be done but I would not advise you to do it with this particular algorithm. I think you would be interested in the work of Jatin Chowdhury[1] as well as the…

Copy pasting my a reply to a similar question Short answer is yes! Previous work has shown that we can obtain very good results from controlling DDSP models from midi input. The so…

Short answer is yes! Previous work has shown that we can obtain very good results from controlling DDSP models from midi input. The solutions I am familiar with employ a two stage …

Thank you! It was made with figma.