17 days of machine listening. Timeline: Aug 16 to Sep 1, 2026.
Can a machine hear what a person hears?
Auracle = aura + oracle, landing on auricle, the outer ear.
Every day follows the same three beats:
1. The ear does this. 2. The machine does this. 3. Here is where the machine fails.
The third beat is the main goal. Every learning log on the internet has resources and code. However, not all of them explain why it fails from a humanistic perspective.
| Day | Title | Status |
|---|---|---|
| 01 | Air pressure becomes a number | done |
| 02 | Frequency becomes pitch | done |
| 03 | Amplitude becomes loudness | done |
| 04 | The perceptual frequency axis | done |
| 05 | Timbre, or why a violin is not a flute | done |
| 06 | Pitch that isn't there | |
| 07 | The beat is not in the signal | |
| 08 | The cocktail party problem | |
| 09 | Source separation, the learned answer | |
| 10 | Tonality and key | |
| 11 | Repetition, structure, and expectation | |
| 12 | DSP in C++ | |
| 13 | Auto-tagging: from features to labels | |
| 14 | Deep machine listening | |
| 15 | The original question | |
| 16 | Did any of it beat chance? | |
| 17 | Ship |
Full plan: docs/plans/2026-08-16-auracle-design.md
Daily logs: docs/log/
Filled in on day 16, after every claim in this repo is tested against a shuffled-label null. Anything that does not survive gets retracted here, visibly.
| Claim | Day | Beat chance? |
|---|---|---|
| pending |
uv venv
source .venv/bin/activate
uv pip install -r requirements.txtsource .venv/bin/activate
python labs/day-01-sampling/aliasing.pyBuilt from primary sources: papers, library documentation, and the canonical texts. The backbone reference is Meinard Müller, Fundamentals of Music Processing (FMP notebooks, free and executable). Per-day citations live in each daily log.
MIT for the code. Written notes are the author's.