I would like to learn how to translate relatively high-level ideas like in the presentation you shared (thanks!) to actual equations to code. Are there any good resources that you would recommend (YouTube channels, books, etc.)? They don't have to be consciousness-related but I would prefer to avoid books on modeling, say, mechanical things because they usually end up over-relying on the reader's background, e.g., in physics. I am more interested in learning how to express "novel" ideas in equations and code.
Perhaps GPT-like models are already capable enough to do math, but they need to store what we call mathematical reasoning as one of many distinct processing pathway and tap into it whenever the context is appropriate.
Easy to say obviously but there's some promising work in this direction[1]
I think you'll find plenty of people who find that DAWs and music theory help them better find self-expression and celebrate life through their music. Any tool or framework that opens up new modes of achieving that self-expression should be celebrated, not shunned because it isn't as "pure" as more time and labor intensive methods. Would you rather someone be forced to dedicate a significant amount of time to studying music and art creation just to be able to find that self-expression?
I strongly recommend this presentation: "John Baez: "Symmetric Monoidal Categories A Rosetta Stone"[0]. It is easy to get lost in the ocean of theorems and definitions and overlook some powerful core concepts.
Just tested it on a Samsung Galaxy phone and there does seem to be an issue with longer audio files.
I'm working on it, in the meantime I've added settings to reduce computational load particularly for smartphones.
I would love to work on something like that, I have a couple ideas regarding ways to implement it.
However I don't know if I have the time to do it, as there are so many concepts I'm trying to channel through code. Hopefully as I build more computational tools I will increase my bandwidth.
Providing visual tools for phonetic assistance is definitely something I've had in mind for a while and solving the dataset building problem should solve that along the way.
As of now, you can:
1) set the amount_sphere_tube slider to 1
2) decrease the playback_rate to 0.1(in the GUI on the right)
3) on the media controller, go to options(the naming might vary depending on the browser) and set the playback rate to normal or x1.
This should give you maximal temporal resolution.
One way features can be further highlighted by generating embeddings from magenta ddsp[0]. Speech sounds are fairly complex though so I don't know how models built on music data would generalize to them.
I think tech to do is is there, but for the time being it seems to be scattered around fairly siloed fields.
I also tried to use live voice recordings but there are latency issues with the subset of the Web Audio API I'm currently using. However there definitely is value in having a live, spatial feedback of pronunciation.
