Back to browse
Resonate – Low-latency, high-resolution spectral analysis

Resonate – Low-latency, high-resolution spectral analysis

by arjf·Jun 6, 2026·3 points·2 comments

AI Analysis

●●SolidNiche GemBig Brain

No-buffering spectral analysis that updates per sample, but audio DSP is a tiny audience.

Strengths
  • Per-sample updates with no buffering enables genuine low-latency audio processing.
  • EWMA-based resonator model reduces computational cost to handful of arithmetic operations.
  • Best paper award at ICMC and talk at Audio Developer Conference validate the approach.
Weaknesses
  • Author admits techniques aren't new, just combined in novel way—incremental rather than breakthrough.
  • Heavy on math formulas, light on practical implementation examples or code libraries.
Category
Target Audience

Audio developers, DSP researchers, music technologists

Similar To

librosa · Essentia · phase vocoder implementations

Post Description

Last April I shared about my Resonate project here (https://news.ycombinator.com/item?id=43694157)

A lot has happened since: the work I presented in much more detail at last June's International Computer Music Conference (ICMC) got best paper award. I also gave a talk at the Audio Developer Conference in Bristol last November, the video is on YouTube).

This year's work, which I recently presented at this year's ICMC, starts with known techniques from the phase vocoder literature to build self-tuning filter banks that extract very efficiently the frequency components that are actually present in the input signal. Overview on the project website, more details in the papers, including applications to super-resolution spectrograms and re-synthesis experiments.

As many people have pointed out, none of the techniques I have used are new (some of them even have different names across different fields), but I haven't seen them applied together in this way, and to me the results are incredibly satisfying and sometimes look magical. See for example this demo: https://youtu.be/LasdoIJJkw8

Of course the best way to experience in person is through the free demo app: https://alexandrefrancois.org/Oscillators

Looking forward to feedback from the community!

Similar Projects

AI/ML●●Solid

True and4500 FPS Edge Detection at 1K (CPU-only)

4500 FPS edge detection on CPU via bitwise hacking; clever but unclear practical advantage over GPU.

WizardryBig Brain
andrespi
103mo ago