I went down a similar rabbit hole at the start of my PhD and I wish I’d written more of it up. One of my theories is that they combined effects quite often. For example, “harder better faster stronger” seems more likely to be a talk box recorded for a single note, then looped, then run through an AutoTune rack unit with MIDI inputs to repitch it. I mention this a little bit in a talk I have at ADC 2022 https://youtu.be/uX-FVtQT0PQ?feature=shared
This is cool - there’s some similar work here https://arxiv.org/pdf/2402.01571 which uses spiking neural networks (essentially Dirac pulses). I think the next step for this would be to learn a tonal embedding of the source alongside the event embedding so that you don’t have to rely on physically modelled priors. There’s some interesting work on guitar amp tone modelling that’s doing this already https://zenodo.org/records/14877373
This is a hypothesis put forward by Gerald Langner in the last chapter of “The Neural Code of Pitch and Harmony” 2015. I personally think he was on to something but sadly he died in 2016 before he could promote the work
I’m the author of the high resolution guitar model posted in a comment above. I have a drum transcription model that I’m getting ready for release soon which should be state of the art for this. I’ll try to update this thread when I’m done
Hydrofoil from Sorrento to Capri in choppy seas, on our honeymoon. Was the stuff of nightmares. My wife said we’d have to live on Capri because she was never setting foot on a boat again
It sounds like you’ve found it already but th original pYin implementation is in the VAMP plugin. Simon Dixon is my PhD supervisor but he’s quite busy. Feel free to email me questions in my the meantime. j.x.riley@ the same university as Simon. There’s also a Python implementation in the librosa library which might have a better license for your purposes.
High latency - agreed but it depends on whether a GPU is available or not. If it is then theoretically CREPE could be real-time. The error rates for pitch recognition are still quite good though for the full CREPE model. I’m interested to see the data on this claim.
Simple techniques like autocorrelation can still recover a missing fundamental. To answer the GP post, using neural networks for this task is overkill for simple, clean signals but it can be desirable if you need a) extremely high accuracy or b) robust results when there are signal degradations like background noise
> how does authorization between the host and the forked work?
On fly.io you get a private network between machines so comms are already secure. For machines outside of fly.io it’s technically possible to connect them using something like Tailscale, but that isn’t the happy path.
> how do I make sure that the unit of work has the right IAM
As shown in the demo, you can customise what gets loaded on boot - I can imagine that you’d use specific creds for services as part of that boot process based on the node’s role.
It’s not been mentioned yet, but if you play music then going to jam sessions is a great way to meet people. You’re all on a journey together toward improving as musicians which helps things to gel. As a jazz musician I can find a jam session in pretty much any city I go to. If you don’t play you can always go just to listen, watch and be inspired
There’s a model for music transcription (audio to midi) called MT3 which takes an end-to-end transformer approach and claims SOTA on some datasets. However, from my own research and comparing with other models it seems that MT3 is very prone to overfitting and the real world results are not as impressive. A similar story seems to be playing out in the comments here
Someone in my PhD lab looked at this and commented that they weren’t that impressed. The authors didn’t account for the fact that ballads and uptempo numbers have vastly different swing ratios (in both cases practically straight) which skews the results. I think rhythmic phenomena and perception are worthy of study but this isn’t a great example imo
I agree that the install is hard on linux but there are prebuilt packages for Windows and MacOS. There's no requirement to use a Raspberry Pi.
A long time ago (2017) I did successfully get Sonic Pi running in Docker but it wasn't straightforward https://github.com/xavriley/sonic-pi-docker If anyone wants to pick this back up I'd be happy to help
For anyone wondering, a lot of work on Sonic Pi recently has gone into integrating an Elixir backend to handle distributed jamming. It has Ableton Link support so it can easily be synced with a DAW and other apps. It can also control external devices via MIDI and OSC protocols more reliably as a result.
At the time Google Books started, “big data” was in vogue and there were data-driven ML approaches to NLP e.g. word2vec, that would have benefited from a large corpus