| Name |
Last commit
|
Last update |
|---|---|---|
| .. | ||
| __init__.py | ||
| autotune.py | ||
| correlate.py | ||
| demos.py | ||
| fetch.py | ||
| grade.py | ||
| kitcheck.py | ||
| loops.py | ||
| model.py | ||
| naming.py | ||
| publish.py | ||
| roles.py | ||
| separate.py | ||
| stempack.py | ||
| vox.py |
librosa's peak-picker finds peaks in whatever onset envelope it is handed, flat ones included: a steady 50 Hz sine yields 84 onsets over six seconds (14/s) and was being filed as drums, which made the bass branch unreachable for exactly the signal it was written for. Onset count is now gated on the frame-RMS crest — ~1.0 for a sustained tone against 3.1-9.5 for anything struck. Measured across MAREA/ANGIE/ME to pick the threshold rather than guess it. Worth recording that crest is a SPARSITY measure, not a percussion one — MAREA's single vocal phrase reads 17.98 — so it only ever gates onset density and is never used alone. HPSS was tried first and rejected: a kick-heavy drum bus reads 0.094 percussive, because HPSS hears a modern kick as harmonic. 18 tests.
| Name |
Last commit
|
Last update |
|---|---|---|
| .. | ||
| __init__.py | Loading commit data... | |
| autotune.py | Loading commit data... | |
| correlate.py | Loading commit data... | |
| demos.py | Loading commit data... | |
| fetch.py | Loading commit data... | |
| grade.py | Loading commit data... | |
| kitcheck.py | Loading commit data... | |
| loops.py | Loading commit data... | |
| model.py | Loading commit data... | |
| naming.py | Loading commit data... | |
| publish.py | Loading commit data... | |
| roles.py | Loading commit data... | |
| separate.py | Loading commit data... | |
| stempack.py | Loading commit data... | |
| vox.py | Loading commit data... |