Hacker News: xavriley

New comment by xavriley in "MAI-Thinking-1"

xavriley — Tue, 02 Jun 2026 20:01:47 +0000

“ We trained it from the ground up on enterprise grade, clean and commercially licensed data, without distillation from third-party models.”

New comment by xavriley in "The vocal effects of Daft Punk"

xavriley — Mon, 05 May 2025 19:34:54 +0000

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

Generative Modelling in Latent Space

xavriley — Tue, 15 Apr 2025 10:56:38 +0000

Article URL: https://sander.ai/2025/04/15/latents.html

Comments URL: https://news.ycombinator.com/item?id=43691147

Points: 14

# Comments: 0

New comment by xavriley in "Show HN: Web Audio Spring-Mass Synthesis"

xavriley — Sat, 15 Mar 2025 07:29:16 +0000

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

New comment by xavriley in "Music as Language (2019) [pdf]"

xavriley — Sun, 24 Nov 2024 03:44:48 +0000

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

New comment by xavriley in "YouTube Video to Tabs and Lyrics"

xavriley — Thu, 15 Aug 2024 17:53:07 +0000

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

New comment by xavriley in "The Limited Value of Multivitamin Supplements"

xavriley — Sat, 29 Jun 2024 10:34:10 +0000

> In 1912, based on research on B vitamins, Polish biochemist Casimir Funk condensed the term vital amines to vitamines.

Casimir Funk is one of the best names I’ve ever heard

New comment by xavriley in "The hovercraft's time might have arrived"

xavriley — Mon, 15 Jan 2024 18:00:34 +0000

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

New comment by xavriley in "TuneNN: A transformer-based network model for pitch detection"

xavriley — Tue, 19 Dec 2023 22:39:44 +0000

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.

New comment by xavriley in "TuneNN: A transformer-based network model for pitch detection"

xavriley — Tue, 19 Dec 2023 22:35:03 +0000

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.

New comment by xavriley in "TuneNN: A transformer-based network model for pitch detection"

xavriley — Tue, 19 Dec 2023 22:31:52 +0000

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

New comment by xavriley in "Rethinking serverless with FLAME"

xavriley — Wed, 06 Dec 2023 20:30:08 +0000

> 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.

New comment by xavriley in "Llark: An LLM which understands music"

xavriley — Thu, 12 Oct 2023 17:59:09 +0000

Examples are here: http://storage.googleapis.com/music2text-public/index.html

Llark: An LLM which understands music

xavriley — Thu, 12 Oct 2023 17:54:02 +0000

Article URL: https://arxiv.org/abs/2310.07160

Comments URL: https://news.ycombinator.com/item?id=37860517

Points: 2

# Comments: 1

New comment by xavriley in "Ask HN: Where have you found community outside of work?"

xavriley — Tue, 30 May 2023 18:57:17 +0000

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

New comment by xavriley in "Donut: OCR-Free Document Understanding Transformer"

xavriley — Mon, 29 May 2023 12:16:41 +0000

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

New comment by xavriley in "Petrucci Music Library"

xavriley — Thu, 18 May 2023 08:07:14 +0000

This sort of exists already at https://classtab.org/

There's also https://www.classclef.com/ which appears to be a tidier fork of the above

New comment by xavriley in "Downbeat delays are a key component of swing in jazz"

xavriley — Fri, 11 Nov 2022 21:09:02 +0000

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

New comment by xavriley in "Sonic Pi – The Live Coding Music Synth for Everyone"

xavriley — Tue, 08 Nov 2022 11:25:08 +0000

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

New comment by xavriley in "Sonic Pi – The Live Coding Music Synth for Everyone"

xavriley — Tue, 08 Nov 2022 08:50:58 +0000

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.