Spaces:
Running
Running
Upload feature_extractor_cpu.py with huggingface_hub
Browse files- feature_extractor_cpu.py +978 -0
feature_extractor_cpu.py
ADDED
|
@@ -0,0 +1,978 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# feature_extractor_cpu.py β HF Spaces CPU Basic variant.
|
| 2 |
+
# Identical to feature_extractor.py. shifts=5 is preserved as required.
|
| 3 |
+
# Expected processing time on CPU Basic (2 vCPU): ~33β136 min per track
|
| 4 |
+
# depending on track length. This is expected β do not reduce shifts.
|
| 5 |
+
# No GPU code. No spaces.GPU decorator. Do not import the 'spaces' package.
|
| 6 |
+
|
| 7 |
+
import numpy as np
|
| 8 |
+
import librosa, torch, openl3, warnings
|
| 9 |
+
from demucs.pretrained import get_model
|
| 10 |
+
from demucs.apply import apply_model
|
| 11 |
+
from scipy.stats import entropy
|
| 12 |
+
from scipy.signal import butter, sosfilt, resample_poly
|
| 13 |
+
import pyloudnorm as pyln
|
| 14 |
+
|
| 15 |
+
warnings.filterwarnings('ignore'); EPS = 1e-10
|
| 16 |
+
|
| 17 |
+
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 18 |
+
# ENG_DIMS β ordered names for every element of the eng_vec returned by
|
| 19 |
+
# extract_mir_features(). Used by lane_model.py and analyze_submissions.py
|
| 20 |
+
# so that dimension names and indices are never hardcoded in two places.
|
| 21 |
+
#
|
| 22 |
+
# DESIGN RATIONALE β SPLITTING COMPOSITE DIMENSIONS
|
| 23 |
+
# ββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 24 |
+
# Every dimension here is intended to be atomic: one measurable quantity,
|
| 25 |
+
# one conceptual meaning. Dimensions that previously bundled distinct concepts
|
| 26 |
+
# have been decomposed. The affected cases are documented below.
|
| 27 |
+
#
|
| 28 |
+
# 1. vocal_prominence (old) β vocal_level + vocal_presence + vocal_brightness
|
| 29 |
+
# The old single ratio (vocal RMS / total RMS) conflated three independent
|
| 30 |
+
# questions: how loud are the vocals when they sing? how much of the song
|
| 31 |
+
# has singing at all? how upfront/forward do the vocals sit spectrally?
|
| 32 |
+
# A track can have loud but infrequent vocals (high level, low presence),
|
| 33 |
+
# or frequent but spectrally buried vocals (high presence, low brightness).
|
| 34 |
+
# These are now three separate dimensions.
|
| 35 |
+
#
|
| 36 |
+
# 2. drum_punch (kept, modified in v4) + drum_prominence (new in v3)
|
| 37 |
+
# drum_punch is the crest factor of the drum stem gated by drum_confidence.
|
| 38 |
+
# drum_prominence is the drum stem's RMS share of the total mix.
|
| 39 |
+
#
|
| 40 |
+
# Before v4, drum_punch was a raw crest factor: peak(drum_stem) /
|
| 41 |
+
# rms(drum_stem). This produced false positives for songs with no drums:
|
| 42 |
+
# htdemucs leaks guitar strum transients into the drum stem, giving the
|
| 43 |
+
# stem a tiny RMS denominator but real peaks β inflated crest factor.
|
| 44 |
+
# drum_prominence did not protect against this because it measures the
|
| 45 |
+
# stem's share of the total mix, not the stem's internal peak-to-RMS ratio.
|
| 46 |
+
#
|
| 47 |
+
# Fix (v4): drum_punch is now multiplied by drum_confidence [0,1], a
|
| 48 |
+
# frequency-domain drum detection score. Supporting sub-dimensions:
|
| 49 |
+
#
|
| 50 |
+
# drum_kick_presence β (v5, unchanged in v6) Drum stem's dominance in the
|
| 51 |
+
# 40β120 Hz kick band, measured as:
|
| 52 |
+
# RMS(drum_stem, 40β120 Hz) / RMS(full_mix, 40β120 Hz)
|
| 53 |
+
# When a real kick drum is present, the drum stem
|
| 54 |
+
# provides most of the mix's sub-bass energy (ratio
|
| 55 |
+
# 0.50β0.90). Guitar bleed: kick_dom β 0.05β0.30.
|
| 56 |
+
#
|
| 57 |
+
# drum_cymbal_presence β (v6 REDESIGN) HPSS-based sustained energy in the
|
| 58 |
+
# 4β10 kHz band of the drum stem. Measures crash and
|
| 59 |
+
# ride cymbal ring-out as opposed to transient hi-hat
|
| 60 |
+
# clicks (which go to hihat_presence below).
|
| 61 |
+
#
|
| 62 |
+
# Formula:
|
| 63 |
+
# sustained_frac = H_energy(4-10kHz) / total_energy(4-10kHz)
|
| 64 |
+
# band_prom = RMS(mag, 4-10kHz) / RMS(mag, all)
|
| 65 |
+
# cymbal_presence = (sustained_frac Γ band_prom) / CYMBAL_SAT
|
| 66 |
+
# (clamped to [0, 1])
|
| 67 |
+
#
|
| 68 |
+
# WHY v5 dominance ratio (8-16 kHz) FAILED:
|
| 69 |
+
# The v5 formula = RMS(drum_stem, 8-16kHz) / RMS(mix, 8-16kHz)
|
| 70 |
+
# collapses when a bright guitar or synth pad adds energy
|
| 71 |
+
# at 8-16 kHz alongside real hi-hats. The mix denominator
|
| 72 |
+
# inflates while the drum numerator is unchanged, pushing the
|
| 73 |
+
# ratio below the lane mean even with cymbals throughout.
|
| 74 |
+
# This caused "cymbal presence thinner than what I feature"
|
| 75 |
+
# rejections for tracks verified to have hi-hats and crashes.
|
| 76 |
+
#
|
| 77 |
+
# The HPSS H component captures ring-out / shimmer β the
|
| 78 |
+
# characteristic of crashes and rides β regardless of what
|
| 79 |
+
# other sources contribute to the full mix at those frequencies.
|
| 80 |
+
#
|
| 81 |
+
# hihat_presence β (v6 NEW) Onset density of the HPSS percussive (P)
|
| 82 |
+
# component in 8β14 kHz, as a fraction of HIHAT_ONSET_SAT.
|
| 83 |
+
#
|
| 84 |
+
# Hi-hats are short transients β appear in P component.
|
| 85 |
+
# Guitar chord rings at 8-14 kHz are sustained β appear in H.
|
| 86 |
+
# Soft-masking by P/(mag+EPS) then zeroing non-hihat bins
|
| 87 |
+
# isolates percussive 8-14 kHz content. Onset detection on
|
| 88 |
+
# this signal counts hi-hat events per second.
|
| 89 |
+
#
|
| 90 |
+
# Guitar staccato transients at 8-14 kHz are much weaker
|
| 91 |
+
# than real hi-hat transients and fall below the
|
| 92 |
+
# onset_detect delta threshold.
|
| 93 |
+
#
|
| 94 |
+
# drum_confidence β (v6 updated) Composite [0,1] drum detection score:
|
| 95 |
+
# 0.55 Γ clamp(kick_dom / DRUM_KICK_SAT, 0, 1)
|
| 96 |
+
# + 0.30 Γ hihat_presence (already in [0,1])
|
| 97 |
+
# + 0.15 Γ cymbal_presence (already in [0,1])
|
| 98 |
+
#
|
| 99 |
+
# Hi-hat weight raised vs. v5 cymbal weight (0.30 vs 0.40)
|
| 100 |
+
# because onset density at 8-14 kHz is near-impossible to
|
| 101 |
+
# trigger without real drum content. A drumless acoustic
|
| 102 |
+
# track cannot produce rapid regular transients in that band.
|
| 103 |
+
#
|
| 104 |
+
# drum_punch (index 2): drum_crest_raw Γ drum_confidence (unchanged gate mechanism).
|
| 105 |
+
#
|
| 106 |
+
# 3. bass_tightness (kept) + bass_prominence (new in v3)
|
| 107 |
+
# Identical reasoning to drum_punch/drum_prominence above.
|
| 108 |
+
#
|
| 109 |
+
# 4. guitar_energy (old) β other_prominence (renamed in v3)
|
| 110 |
+
# With htdemucs_6s (v8), the "other" stem is now cleaner: guitar and piano
|
| 111 |
+
# are extracted into dedicated stems (indices 4 and 5). other_prominence now
|
| 112 |
+
# reflects only synths, strings, pads, and miscellaneous non-vocal content.
|
| 113 |
+
#
|
| 114 |
+
# 5. egtr_presence + egtr_level (v8 NEW)
|
| 115 |
+
# Two new dimensions operating on the dedicated guitar stem from htdemucs_6s.
|
| 116 |
+
# See below for full rationale.
|
| 117 |
+
#
|
| 118 |
+
# RENAMES (done in v3):
|
| 119 |
+
# complexity β harmonic_complexity (chroma entropy β general complexity)
|
| 120 |
+
# dynamics β lufs_variation (std(LUFS) β all kinds of dynamics)
|
| 121 |
+
#
|
| 122 |
+
# Index history:
|
| 123 |
+
# Indices 0β25: identical to v3.
|
| 124 |
+
# Indices 26β27: added in v4, semantics updated in v5 (dominance ratio).
|
| 125 |
+
# Index 26: unchanged in v6 (kick dominance ratio).
|
| 126 |
+
# Index 27: v6 redesign β was 8-16kHz dominance ratio, now HPSS sustained
|
| 127 |
+
# fraction in 4-10kHz. INCOMPATIBLE with v5 cache entries.
|
| 128 |
+
# Index 28: v6 updated weights (was 0.60Γkick+0.40Γcymbal).
|
| 129 |
+
# Index 29: v6 NEW β hihat_presence.
|
| 130 |
+
# Indices 30β31: v8 NEW β egtr_presence, egtr_level.
|
| 131 |
+
# htdemucs switched from 4-stem (htdemucs) to 6-stem (htdemucs_6s).
|
| 132 |
+
# total_rms now includes guitar_rms + piano_rms (more accurate
|
| 133 |
+
# stem-sum denominator). All v7 cache entries are incompatible.
|
| 134 |
+
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 135 |
+
ENG_DIMS = [
|
| 136 |
+
"lufs", # 0: Integrated loudness (LUFS)
|
| 137 |
+
"crest_factor", # 1: Peak-to-RMS ratio (global mix)
|
| 138 |
+
"drum_punch", # 2: Drum stem crest factor Γ drum_confidence (gated)
|
| 139 |
+
"drum_prominence", # 3: Drum stem RMS / total mix RMS (mix presence)
|
| 140 |
+
"stereo_width", # 4: Mid-side energy ratio
|
| 141 |
+
"brightness", # 5: Spectral centroid of mix (Hz)
|
| 142 |
+
"harmonic_complexity", # 6: Chroma entropy (harmonic diversity only)
|
| 143 |
+
"clip_num_events", # 7: Number of separate clipping events
|
| 144 |
+
"clip_total", # 8: Total clipped samples
|
| 145 |
+
"clip_ratio", # 9: Clipped samples / total samples
|
| 146 |
+
"clip_max_run", # 10: Longest consecutive clipping run (samples)
|
| 147 |
+
"clip_mean_run", # 11: Mean clipping run length across all events
|
| 148 |
+
"other_prominence", # 12: Other stem (synth/pad/strings) RMS / total mix RMS
|
| 149 |
+
"vocal_level", # 13: Vocal stem RMS / total mix RMS (loudness when present)
|
| 150 |
+
"vocal_presence", # 14: Fraction of frames with active vocal signal (0β1)
|
| 151 |
+
"vocal_brightness", # 15: Spectral centroid of vocal stem (Hz)
|
| 152 |
+
"chorus_lift", # 16: Max short-term LUFS minus median (LU)
|
| 153 |
+
"crispness", # 17: Zero-crossing rate (high-frequency texture)
|
| 154 |
+
"clarity", # 18: Spectral flatness (tonal vs. noise-like character)
|
| 155 |
+
"length_s", # 19: Track length in seconds
|
| 156 |
+
"lufs_variation", # 20: Std of short-term LUFS
|
| 157 |
+
"peak_lufs", # 21: Max short-term LUFS
|
| 158 |
+
"rolloff", # 22: Spectral rolloff (Hz)
|
| 159 |
+
"bass_tightness", # 23: Bass stem crest factor
|
| 160 |
+
"bass_prominence", # 24: Bass stem RMS / total mix RMS
|
| 161 |
+
"phase_corr", # 25: L/R phase correlation
|
| 162 |
+
# ββ Drum sub-dimensions (v4+, semantics per version noted) ββββββββββββββοΏ½οΏ½
|
| 163 |
+
"drum_kick_presence", # 26: RMS(drum stem, 40β120 Hz) / RMS(full mix, 40β120 Hz) [v5, unchanged]
|
| 164 |
+
"drum_cymbal_presence",# 27: HPSS sustained fraction Γ band prominence in 4β10 kHz [v6]
|
| 165 |
+
"drum_confidence", # 28: 0.55Γkick_conf + 0.30Γhihat_conf + 0.15Γcymbal_conf [v6]
|
| 166 |
+
"hihat_presence", # 29: Onset density of percussive 8β14 kHz drum component [v6 NEW]
|
| 167 |
+
# ββ Electric guitar dimensions (v8 NEW β htdemucs_6s guitar stem) ββββββββ
|
| 168 |
+
"egtr_presence", # 30: Composite electric guitar detection score [0,1] [v8 NEW]
|
| 169 |
+
"egtr_level", # 31: egtr_presence Γ (guitar_rms / total_rms) β guitar mix level [v8 NEW]
|
| 170 |
+
]
|
| 171 |
+
|
| 172 |
+
# ββ Vocal activity detection threshold βββββββββββββββββββββββββββββββββββββββ
|
| 173 |
+
# Frames whose RMS exceeds this value are counted as active vocal frames.
|
| 174 |
+
# 0.01 linear β -40 dBFS.
|
| 175 |
+
VOCAL_ACTIVITY_THRESHOLD = 0.01
|
| 176 |
+
|
| 177 |
+
# ββ Drum band analysis constants (v6) ββββββββββββββββββββββββββββββββββββββββ
|
| 178 |
+
#
|
| 179 |
+
# KICK (dominance ratio, unchanged from v5):
|
| 180 |
+
# DRUM_KICK_SAT = 0.55
|
| 181 |
+
# The kick dominance ratio at which kick_conf saturates at 1.0. Real kick
|
| 182 |
+
# drum: drum stem provides 50β90 % of mix kick-band energy β conf = 1.0.
|
| 183 |
+
# Acoustic guitar bleed: kick_dom β 0.05β0.30 β conf β€ 0.55.
|
| 184 |
+
#
|
| 185 |
+
# CYMBAL (HPSS sustained fraction, 4β10 kHz, v6):
|
| 186 |
+
# CYMBAL_BAND_FMIN / FMAX = 4000β10000 Hz
|
| 187 |
+
# Crash and ride cymbal fundamental energy. Crashes ring in 3β8 kHz;
|
| 188 |
+
# rides shimmer in 5β12 kHz. 4-10 kHz captures the core sustained content
|
| 189 |
+
# of both without extending into the hi-hat domain (8-14 kHz).
|
| 190 |
+
# CYMBAL_SAT = 0.20
|
| 191 |
+
# Value of (sustained_frac Γ band_prom) at which cymbal_presence = 1.0.
|
| 192 |
+
# Estimated: crash-heavy track β sustained_frac β 0.60, band_prom β 0.35
|
| 193 |
+
# β product β 0.21. Kick+snare only β product β 0.05β0.10.
|
| 194 |
+
# Tune up if lane refs with strong crashes score < 0.70; tune down if
|
| 195 |
+
# kick-only tracks score > 0.40.
|
| 196 |
+
#
|
| 197 |
+
# HI-HAT (HPSS onset density, 8β14 kHz, v6 NEW):
|
| 198 |
+
# HIHAT_BAND_FMIN / FMAX = 8000β14000 Hz
|
| 199 |
+
# Closed and open hi-hat fundamental energy. Concentrated above 8 kHz;
|
| 200 |
+
# stopping at 14 kHz avoids excessive noise-floor sensitivity at the
|
| 201 |
+
# top of the drum stem frequency range.
|
| 202 |
+
# HIHAT_ONSET_SAT = 5.0 (onsets/sec)
|
| 203 |
+
# Onset rate at which hihat_presence = 1.0. 16th notes at 75 bpm = 5/sec;
|
| 204 |
+
# 8th notes at 150 bpm = 5/sec. Most steady hi-hat patterns in rock/pop
|
| 205 |
+
# fall in the 3β8 onsets/sec range. Tune down if lane refs with active
|
| 206 |
+
# hi-hats score < 0.60; tune up if drumless tracks score > 0.15.
|
| 207 |
+
#
|
| 208 |
+
# DRUM CONFIDENCE WEIGHTS (v6):
|
| 209 |
+
# DRUM_KICK_WEIGHT = 0.55 (was 0.60 in v5)
|
| 210 |
+
# DRUM_HIHAT_WEIGHT = 0.30 (new; replaces cymbal_weight contribution)
|
| 211 |
+
# DRUM_CYMBAL_WEIGHT = 0.15 (new; crash/ride as secondary gate input)
|
| 212 |
+
# Sum = 1.0 β fully normalized confidence score.
|
| 213 |
+
#
|
| 214 |
+
# Hi-hat raised to 0.30: onset density at 8-14 kHz is nearly impossible to
|
| 215 |
+
# produce without a real drum kit. Acoustic guitars, hand percussion, and
|
| 216 |
+
# electronic pads without a dedicated hi-hat pattern will all score near 0.
|
| 217 |
+
# This makes drum_confidence a much stronger gate against false positives.
|
| 218 |
+
#
|
| 219 |
+
DRUM_KICK_FMIN = 40.0 # Hz β kick fundamental lower bound
|
| 220 |
+
DRUM_KICK_FMAX = 120.0 # Hz β kick fundamental upper bound
|
| 221 |
+
DRUM_KICK_SAT = 0.55 # kick dominance ratio at kick_conf = 1.0
|
| 222 |
+
|
| 223 |
+
CYMBAL_BAND_FMIN = 4000.0 # Hz β crash/ride lower bound
|
| 224 |
+
CYMBAL_BAND_FMAX = 10000.0 # Hz β crash/ride upper bound
|
| 225 |
+
CYMBAL_SAT = 0.20 # (sustained_frac Γ band_prom) at cymbal_presence = 1.0
|
| 226 |
+
|
| 227 |
+
HIHAT_BAND_FMIN = 8000.0 # Hz β hi-hat lower bound
|
| 228 |
+
HIHAT_BAND_FMAX = 14000.0 # Hz β hi-hat upper bound
|
| 229 |
+
HIHAT_ONSET_SAT = 5.0 # onsets/sec at hihat_presence = 1.0
|
| 230 |
+
|
| 231 |
+
DRUM_KICK_WEIGHT = 0.55 # weight for kick_conf in drum_confidence
|
| 232 |
+
DRUM_HIHAT_WEIGHT = 0.30 # weight for hihat_presence in drum_confidence
|
| 233 |
+
DRUM_CYMBAL_WEIGHT = 0.15 # weight for cymbal_presence in drum_confidence
|
| 234 |
+
|
| 235 |
+
# ββ Electric guitar detection constants (v8) ββββββββββββββββββββββββββββββββββ
|
| 236 |
+
#
|
| 237 |
+
# EGTR_MID_FMIN / FMAX = 200β5000 Hz
|
| 238 |
+
# Core range of electric guitar fundamentals and dominant harmonics.
|
| 239 |
+
# Low E string = 82 Hz; high E string = 1318 Hz. Upper harmonics and
|
| 240 |
+
# distortion products extend to 5 kHz. Starting at 200 Hz avoids bleed
|
| 241 |
+
# from the bass stem into the guitar stem. Stopping at 5 kHz keeps the
|
| 242 |
+
# measure out of the hi-hat / pick-noise band (handled by drum dims).
|
| 243 |
+
#
|
| 244 |
+
# EGTR_PICK_ONSET_SAT = 4.0 (onsets/sec)
|
| 245 |
+
# Onset rate at which picking_density = 1.0. 8th notes at 120 bpm = 4/sec;
|
| 246 |
+
# 16th notes at 60 bpm = 4/sec. Steady rhythm guitar in rock/pop lands
|
| 247 |
+
# in the 2β6 onsets/sec range.
|
| 248 |
+
# Tune DOWN if lane refs with active rhythm guitar score < 0.50.
|
| 249 |
+
# Tune UP if piano-only or pad-heavy tracks score above 0.30.
|
| 250 |
+
#
|
| 251 |
+
# EGTR_FLATNESS_SAT = 0.25
|
| 252 |
+
# Mid-band spectral flatness at which mid_saturation = 1.0.
|
| 253 |
+
# Clean electric guitar: 0.05β0.15. Crunchy/overdriven: 0.10β0.30.
|
| 254 |
+
# Full distortion lead: 0.20β0.40. Piano: 0.02β0.08. Acoustic: 0.03β0.12.
|
| 255 |
+
# 0.25 is intentionally generous β rewards any electric guitar content,
|
| 256 |
+
# not only distorted playing. Clean electric guitar (Fender clean tone)
|
| 257 |
+
# will score low here; such tracks still score via picking_density.
|
| 258 |
+
#
|
| 259 |
+
# EGTR_PICK_WEIGHT = 0.65 β primary gate: rhythmic attack events
|
| 260 |
+
# EGTR_FLAT_WEIGHT = 0.35 β secondary: harmonic saturation (rewards dirt)
|
| 261 |
+
#
|
| 262 |
+
# TUNING GUIDANCE (post first training run):
|
| 263 |
+
# Check the printed standards table for egtr_presence and egtr_level.
|
| 264 |
+
# Lane refs with active electric guitar: egtr_presence β₯ 0.50 (ideally 0.60β0.90)
|
| 265 |
+
# Non-lane refs without guitar: egtr_presence β€ 0.20
|
| 266 |
+
# If guitar tracks score 0.20β0.35: lower EGTR_PICK_ONSET_SAT (4.0 β 2.5)
|
| 267 |
+
# and/or lower EGTR_FLATNESS_SAT (0.25 β 0.15).
|
| 268 |
+
# If piano/pad tracks score above 0.30: raise EGTR_PICK_ONSET_SAT or
|
| 269 |
+
# reduce EGTR_FLAT_WEIGHT to down-weight the flatness component.
|
| 270 |
+
#
|
| 271 |
+
EGTR_MID_FMIN = 200.0 # Hz β guitar mid-band lower bound
|
| 272 |
+
EGTR_MID_FMAX = 5000.0 # Hz β guitar mid-band upper bound
|
| 273 |
+
EGTR_PICK_ONSET_SAT = 4.0 # onsets/sec at picking_density = 1.0
|
| 274 |
+
EGTR_FLATNESS_SAT = 0.25 # flatness value at mid_saturation = 1.0
|
| 275 |
+
EGTR_PICK_WEIGHT = 0.65 # weight for picking_density in egtr_presence
|
| 276 |
+
EGTR_FLAT_WEIGHT = 0.35 # weight for mid_saturation in egtr_presence
|
| 277 |
+
|
| 278 |
+
|
| 279 |
+
device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 280 |
+
demucs_model = get_model('htdemucs_6s') # v8: 6-stem model (adds guitar + piano stems)
|
| 281 |
+
demucs_model.to(device)
|
| 282 |
+
|
| 283 |
+
# htdemucs_6s stem order: 0=drums, 1=bass, 2=other, 3=vocals, 4=guitar, 5=piano
|
| 284 |
+
_STEM_DRUMS = 0
|
| 285 |
+
_STEM_BASS = 1
|
| 286 |
+
_STEM_OTHER = 2
|
| 287 |
+
_STEM_VOCALS = 3
|
| 288 |
+
_STEM_GUITAR = 4 # v8 NEW β dedicated electric/acoustic guitar stem
|
| 289 |
+
_STEM_PIANO = 5 # v8 NEW β dedicated piano stem
|
| 290 |
+
|
| 291 |
+
|
| 292 |
+
def get_stems(path):
|
| 293 |
+
wav, _ = librosa.load(path, sr=demucs_model.samplerate, mono=False)
|
| 294 |
+
if wav.ndim == 1: wav = np.stack([wav, wav])
|
| 295 |
+
ref = torch.from_numpy(wav).to(device)
|
| 296 |
+
ref_std = ref.std() + EPS
|
| 297 |
+
ref = (ref - ref.mean()) / ref_std
|
| 298 |
+
with torch.no_grad():
|
| 299 |
+
sources = apply_model(demucs_model, ref.unsqueeze(0), shifts=5, split=True)[0]
|
| 300 |
+
return (sources * ref_std.cpu().item()).cpu().numpy()
|
| 301 |
+
|
| 302 |
+
|
| 303 |
+
def _measure_clipping(y, threshold=0.999):
|
| 304 |
+
"""
|
| 305 |
+
Returns all five clipping dimensions as individual floats.
|
| 306 |
+
|
| 307 |
+
threshold=0.999 (~-0.009 dBFS) avoids flagging legitimately loud
|
| 308 |
+
transient peaks that just touch near-full-scale without flat-topping.
|
| 309 |
+
|
| 310 |
+
Returns: (num_events, total_samples, ratio, max_run, mean_run)
|
| 311 |
+
"""
|
| 312 |
+
clipped = np.abs(y) >= threshold
|
| 313 |
+
total = int(np.sum(clipped))
|
| 314 |
+
if total == 0:
|
| 315 |
+
return 0.0, 0.0, 0.0, 0.0, 0.0
|
| 316 |
+
|
| 317 |
+
padded = np.concatenate(([False], clipped, [False]))
|
| 318 |
+
diff = np.diff(padded.astype(int))
|
| 319 |
+
run_starts = np.where(diff == 1)[0]
|
| 320 |
+
run_ends = np.where(diff == -1)[0]
|
| 321 |
+
run_lengths = run_ends - run_starts
|
| 322 |
+
|
| 323 |
+
return (
|
| 324 |
+
float(len(run_lengths)),
|
| 325 |
+
float(total),
|
| 326 |
+
float(total / len(y)),
|
| 327 |
+
float(np.max(run_lengths)),
|
| 328 |
+
float(np.mean(run_lengths)),
|
| 329 |
+
)
|
| 330 |
+
|
| 331 |
+
|
| 332 |
+
def _band_rms_abs(y: np.ndarray, sr: int, fmin: float, fmax: float) -> float:
|
| 333 |
+
"""
|
| 334 |
+
Absolute RMS of y in the [fmin, fmax] Hz band (not normalized).
|
| 335 |
+
Used by _compute_drum_bands for kick dominance ratio.
|
| 336 |
+
Returns 0.0 if signal is silent or band is invalid.
|
| 337 |
+
"""
|
| 338 |
+
nyq = sr / 2.0
|
| 339 |
+
lo = max(fmin, 1.0)
|
| 340 |
+
hi = min(fmax, nyq - 1.0)
|
| 341 |
+
if lo >= hi:
|
| 342 |
+
return 0.0
|
| 343 |
+
sos = butter(2, [lo, hi], btype='bandpass', fs=sr, output='sos')
|
| 344 |
+
filtered = sosfilt(sos, y)
|
| 345 |
+
return float(np.sqrt(np.mean(filtered**2)))
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 349 |
+
# ITU-R BS.1770-4 / BS.1775-2 LOUDNESS AND TRUE PEAK IMPLEMENTATION
|
| 350 |
+
#
|
| 351 |
+
# WHY THE OLD FORMULA WAS WRONG
|
| 352 |
+
# βββββββββββββββββββββββββββββββ
|
| 353 |
+
# The original approximation used:
|
| 354 |
+
# lufs β -0.691 + 10 Γ log10(mean(yΒ²))
|
| 355 |
+
# This is RMS-based power in dB, not integrated LUFS. It is missing two
|
| 356 |
+
# mandatory stages defined in ITU-R BS.1770:
|
| 357 |
+
#
|
| 358 |
+
# 1. K-weighting pre-filter β a two-stage IIR filter that:
|
| 359 |
+
# Stage 1: high-shelf boost (+4 dB at high frequencies) modelling
|
| 360 |
+
# the acoustic effect of the listener's head on a microphone.
|
| 361 |
+
# Stage 2: high-pass filter (RLB weighting) removing DC and sub-20 Hz
|
| 362 |
+
# content that inflates RMS but carries no perceived loudness.
|
| 363 |
+
# Together these raise typical music by +1 to +5 dB before squaring.
|
| 364 |
+
#
|
| 365 |
+
# 2. Gating β BS.1770-4 integrates only "active" blocks:
|
| 366 |
+
# Absolute gate: blocks below -70 LUFS excluded (silence/noise floor).
|
| 367 |
+
# Relative gate: second pass excludes blocks more than -10 LU below
|
| 368 |
+
# the ungated mean (rejects very quiet passages).
|
| 369 |
+
# Without gating, quiet intros/outros and noise floors pull the
|
| 370 |
+
# integrated value down, causing systematic under-reading of 2β5 dB.
|
| 371 |
+
#
|
| 372 |
+
# PRACTICAL IMPACT ON THIS SYSTEM
|
| 373 |
+
# ββββββββββββββββββββββββββββββββ
|
| 374 |
+
# Error: 2β4 dB under-reading of integrated LUFS, varying by program material.
|
| 375 |
+
# β’ The Spotify normalization gain calculation was off by that same margin.
|
| 376 |
+
# β’ Lane engineering standards for lufs and peak_lufs were calibrated against
|
| 377 |
+
# the wrong values (consistently wrong, so relative comparisons partially
|
| 378 |
+
# survived β but absolute statements about headroom were incorrect).
|
| 379 |
+
# β’ short-term LUFS (used for peak_lufs, lufs_variation, chorus_lift) had the
|
| 380 |
+
# same error AND lacked K-weighting, so spectral character affected the
|
| 381 |
+
# "loudness" reading in a non-perceptual way.
|
| 382 |
+
# β’ true_peak_dbfs was never returned by the modal worker, making the
|
| 383 |
+
# tp_headroom constraint in apply_streaming_normalization() dead code.
|
| 384 |
+
#
|
| 385 |
+
# FIX SUMMARY (v7)
|
| 386 |
+
# ββββββββββββββββ
|
| 387 |
+
# _compute_integrated_lufs() β pyloudnorm Meter.integrated_loudness()
|
| 388 |
+
# Full BS.1770-4: K-weighting + gating.
|
| 389 |
+
# _compute_short_term_lufs_array() β K-weighted sliding 3s/1s windows, no gate.
|
| 390 |
+
# Same K-weighting as integrated. Replaces the
|
| 391 |
+
# raw librosa.feature.rms()-based st_lufs blocks.
|
| 392 |
+
# _true_peak_dbfs() β 4Γ polyphase oversampling (BS.1775-2) to
|
| 393 |
+
# detect intersample peaks. Returned as third
|
| 394 |
+
# element of extract_mir_features() so the modal
|
| 395 |
+
# worker can include it in the response dict and
|
| 396 |
+
# apply_streaming_normalization() can enforce the
|
| 397 |
+
# -1.0 dBFS true peak ceiling correctly.
|
| 398 |
+
#
|
| 399 |
+
# NOTE: pyloudnorm must be installed: pip install pyloudnorm
|
| 400 |
+
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 401 |
+
|
| 402 |
+
def _kweight_sos(sr: int) -> np.ndarray:
|
| 403 |
+
"""
|
| 404 |
+
BS.1770 K-weighting filter as a stacked SOS array for scipy.signal.sosfilt.
|
| 405 |
+
|
| 406 |
+
Computed directly from the analog prototype parameters in BS.1770 Annex 1
|
| 407 |
+
using the Audio EQ Cookbook (Bristow-Johnson) bilinear transform formulas.
|
| 408 |
+
Does NOT touch pyloudnorm internals β meter._filters internal structure
|
| 409 |
+
has changed between pyloudnorm versions and is not part of its public API.
|
| 410 |
+
|
| 411 |
+
Two cascaded stages:
|
| 412 |
+
Stage 1 β Pre-filter (high-shelf, +4 dB at high frequencies):
|
| 413 |
+
Models the free-field to diffuse-field acoustic correction for the
|
| 414 |
+
effect of the listener's head on a mounted microphone. Raises
|
| 415 |
+
high-frequency energy before mean-square integration so that HF
|
| 416 |
+
content is weighted appropriately by the loudness measure.
|
| 417 |
+
Parameters: f0 = 1500 Hz, dBgain = +4 dB, Q = 1/sqrt(2)
|
| 418 |
+
|
| 419 |
+
Stage 2 β RLB weighting (2nd-order Butterworth high-pass, ~38.1 Hz):
|
| 420 |
+
Removes DC and very low-frequency energy that carries no perceptual
|
| 421 |
+
loudness but would otherwise inflate the mean-square sum.
|
| 422 |
+
Parameters: fc = 38.13494637408312 Hz
|
| 423 |
+
|
| 424 |
+
Returns a (2, 6) ndarray β two SOS sections β ready for sosfilt().
|
| 425 |
+
"""
|
| 426 |
+
# Stage 1: Pre-filter high-shelf (Audio EQ Cookbook high-shelf formula)
|
| 427 |
+
f0 = 1500.0 # Hz β shelf midpoint frequency
|
| 428 |
+
dBgain = 4.0 # dB β shelf gain
|
| 429 |
+
Q = 1.0 / np.sqrt(2) # = 0.7071... (Butterworth Q)
|
| 430 |
+
|
| 431 |
+
A = 10.0 ** (dBgain / 40.0) # sqrt of linear power gain
|
| 432 |
+
w0 = 2.0 * np.pi * f0 / sr # digital frequency (radians/sample)
|
| 433 |
+
alpha = np.sin(w0) / (2.0 * Q) # bandwidth term
|
| 434 |
+
|
| 435 |
+
# High-shelf numerator / denominator (Audio EQ Cookbook, high-shelf)
|
| 436 |
+
b0 = A * ((A + 1) + (A - 1) * np.cos(w0) + 2 * np.sqrt(A) * alpha)
|
| 437 |
+
b1 = -2 * A * ((A - 1) + (A + 1) * np.cos(w0))
|
| 438 |
+
b2 = A * ((A + 1) + (A - 1) * np.cos(w0) - 2 * np.sqrt(A) * alpha)
|
| 439 |
+
a0 = ((A + 1) - (A - 1) * np.cos(w0) + 2 * np.sqrt(A) * alpha)
|
| 440 |
+
a1 = 2 * ((A - 1) - (A + 1) * np.cos(w0))
|
| 441 |
+
a2 = ((A + 1) - (A - 1) * np.cos(w0) - 2 * np.sqrt(A) * alpha)
|
| 442 |
+
|
| 443 |
+
# Second-order section: [b0/a0, b1/a0, b2/a0, 1.0, a1/a0, a2/a0]
|
| 444 |
+
sos_shelf = np.array([[b0/a0, b1/a0, b2/a0, 1.0, a1/a0, a2/a0]])
|
| 445 |
+
|
| 446 |
+
# Stage 2: RLB high-pass (2nd-order Butterworth)
|
| 447 |
+
fc = 38.13494637408312 # Hz
|
| 448 |
+
sos_hp = butter(2, fc / (sr / 2.0), btype='high', output='sos')
|
| 449 |
+
|
| 450 |
+
return np.vstack([sos_shelf, sos_hp]) # shape (2, 6)
|
| 451 |
+
|
| 452 |
+
|
| 453 |
+
def _compute_integrated_lufs(y_stereo: np.ndarray, sr: int) -> float:
|
| 454 |
+
"""
|
| 455 |
+
ITU-R BS.1770-4 integrated LUFS (K-weighted, gated).
|
| 456 |
+
|
| 457 |
+
y_stereo: (2, n_samples) stereo array at sr Hz.
|
| 458 |
+
Returns integrated LUFS as float; returns -70.0 for silent / fully-gated
|
| 459 |
+
signals (pyloudnorm returns -inf in those cases).
|
| 460 |
+
"""
|
| 461 |
+
meter = pyln.Meter(sr)
|
| 462 |
+
data = y_stereo.T.astype(np.float64) # pyloudnorm expects (n_samples, n_ch)
|
| 463 |
+
result = meter.integrated_loudness(data)
|
| 464 |
+
return float(result) if np.isfinite(result) else -70.0
|
| 465 |
+
|
| 466 |
+
|
| 467 |
+
def _compute_short_term_lufs_array(y_stereo: np.ndarray, sr: int,
|
| 468 |
+
window_s: float = 3.0,
|
| 469 |
+
hop_s: float = 1.0) -> np.ndarray:
|
| 470 |
+
"""
|
| 471 |
+
K-weighted short-term loudness in sliding windows (BS.1770, no gating).
|
| 472 |
+
|
| 473 |
+
Applies the same K-weighting filters as integrated LUFS but without the
|
| 474 |
+
absolute/relative gating step, matching the BS.1770 short-term definition.
|
| 475 |
+
Uses the BS.1770 stereo channel-sum formula (G_L = G_R = 1.0):
|
| 476 |
+
L_window = -0.691 + 10 Γ log10(mean_sq_L + mean_sq_R)
|
| 477 |
+
|
| 478 |
+
window_s = 3.0, hop_s = 1.0 matches the original librosa.feature.rms()
|
| 479 |
+
block framing that peak_lufs, lufs_variation, and chorus_lift are based on.
|
| 480 |
+
|
| 481 |
+
y_stereo: (2, n_samples) stereo array at sr Hz.
|
| 482 |
+
Returns array of per-window LUFS values (float64).
|
| 483 |
+
"""
|
| 484 |
+
# Apply K-weighting (BS.1770 pre-filter + RLB high-pass) to each channel.
|
| 485 |
+
# _kweight_sos() returns a single stacked (2, 6) SOS array computed
|
| 486 |
+
# directly from the BS.1770 analog prototype β no pyloudnorm internals used.
|
| 487 |
+
sos = _kweight_sos(sr)
|
| 488 |
+
data = y_stereo.astype(np.float64).copy() # (2, n_samples)
|
| 489 |
+
for ch in range(data.shape[0]):
|
| 490 |
+
data[ch] = sosfilt(sos, data[ch])
|
| 491 |
+
|
| 492 |
+
n_samples = data.shape[1]
|
| 493 |
+
win_len = int(window_s * sr)
|
| 494 |
+
hop_len = max(int(hop_s * sr), 1)
|
| 495 |
+
|
| 496 |
+
results = []
|
| 497 |
+
for start in range(0, max(n_samples - win_len + 1, 1), hop_len):
|
| 498 |
+
block = data[:, start : start + win_len] # (2, win_len)
|
| 499 |
+
ms_sum = float(np.sum(np.mean(block ** 2, axis=1))) # sum over L, R
|
| 500 |
+
results.append(-0.691 + 10.0 * np.log10(ms_sum + EPS))
|
| 501 |
+
|
| 502 |
+
return np.array(results, dtype=np.float64) if results else np.array([-70.0])
|
| 503 |
+
|
| 504 |
+
|
| 505 |
+
def _true_peak_dbfs(y_stereo: np.ndarray) -> float:
|
| 506 |
+
"""
|
| 507 |
+
ITU-R BS.1775-2 true peak level (dBFS), measured via 4Γ oversampling.
|
| 508 |
+
|
| 509 |
+
Standard sample-domain peak measurement misses intersample peaks β peaks
|
| 510 |
+
that occur between samples and can exceed the sample-domain maximum after
|
| 511 |
+
reconstruction. 4Γ oversampling with a polyphase anti-aliasing filter
|
| 512 |
+
(scipy.signal.resample_poly) captures these peaks reliably.
|
| 513 |
+
|
| 514 |
+
Spotify, Apple Music, YouTube, and Tidal all measure true peak at β₯ 4Γ
|
| 515 |
+
oversampling when deciding whether and by how much to apply limiting during
|
| 516 |
+
normalization. -1.0 dBFS TP is the standard limiting ceiling for most DSPs.
|
| 517 |
+
|
| 518 |
+
y_stereo: (2, n_samples) stereo or (n_samples,) mono array.
|
| 519 |
+
Returns peak in dBFS. Typical brick-wall limited master: -0.5 to -0.1 dBFS.
|
| 520 |
+
Silent signal: returns -120.0.
|
| 521 |
+
"""
|
| 522 |
+
oversampled = resample_poly(y_stereo, 4, 1)
|
| 523 |
+
peak_linear = float(np.max(np.abs(oversampled)))
|
| 524 |
+
if peak_linear < EPS:
|
| 525 |
+
return -120.0
|
| 526 |
+
return float(20.0 * np.log10(peak_linear))
|
| 527 |
+
|
| 528 |
+
|
| 529 |
+
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 530 |
+
# CANONICAL STREAMING NORMALIZATION
|
| 531 |
+
#
|
| 532 |
+
# Single source of truth used by both lane_model.py (training) and
|
| 533 |
+
# analyze_submissions.py (inference). Having one implementation guarantees
|
| 534 |
+
# that training and scoring apply identical gain logic β any future change to
|
| 535 |
+
# normalization behaviour only needs to be made in one place.
|
| 536 |
+
#
|
| 537 |
+
# Previously duplicated as:
|
| 538 |
+
# _norm_eng() in lane_model.py (training)
|
| 539 |
+
# apply_streaming_normalization() in analyze_submissions.py (inference)
|
| 540 |
+
# Those two copies were kept manually in sync. They are now replaced by this
|
| 541 |
+
# single function, imported by both callers.
|
| 542 |
+
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 543 |
+
|
| 544 |
+
def apply_streaming_normalization(
|
| 545 |
+
eng: np.ndarray,
|
| 546 |
+
target_lufs: float,
|
| 547 |
+
true_peak_dbfs: "float | None" = None,
|
| 548 |
+
) -> "tuple[np.ndarray, float]":
|
| 549 |
+
"""
|
| 550 |
+
Simulate streaming-platform loudness normalization on an eng vector.
|
| 551 |
+
|
| 552 |
+
Computes the gain the platform would apply to reach target_lufs, then
|
| 553 |
+
shifts the lufs and peak_lufs dimensions by that gain.
|
| 554 |
+
|
| 555 |
+
Only attenuates: gain is capped at 0.0 dB (platforms never boost quiet
|
| 556 |
+
masters β Spotify, Apple Music, etc. leave them quieter than the target).
|
| 557 |
+
|
| 558 |
+
true_peak_dbfs (BS.1775-2, 4Γ oversampled):
|
| 559 |
+
If provided and finite, the gain is also capped so that true peak
|
| 560 |
+
never exceeds -1.0 dBFS post-normalization, matching the hardware
|
| 561 |
+
limiter ceiling used by most streaming DSPs. This cap only activates
|
| 562 |
+
for masters with intersample peaks above -1.0 dBFS. When None or
|
| 563 |
+
non-finite, the cap is skipped (equivalent to tp_headroom = 0.0,
|
| 564 |
+
which is harmless because the 0.0 attenuation cap already applies).
|
| 565 |
+
|
| 566 |
+
Raises ValueError if "lufs" or "peak_lufs" are absent from ENG_DIMS.
|
| 567 |
+
Callers must treat this as a fatal configuration error β it means
|
| 568 |
+
ENG_DIMS was modified without updating this function.
|
| 569 |
+
|
| 570 |
+
Parameters
|
| 571 |
+
----------
|
| 572 |
+
eng : np.ndarray
|
| 573 |
+
Raw engineering feature vector (32 elements, pre-normalization).
|
| 574 |
+
target_lufs : float
|
| 575 |
+
Streaming loudness target in LUFS (e.g. -14.0 for Spotify).
|
| 576 |
+
true_peak_dbfs : float | None
|
| 577 |
+
BS.1775-2 true peak level of the master in dBFS, or None if
|
| 578 |
+
unavailable (true peak cap is skipped when None).
|
| 579 |
+
|
| 580 |
+
Returns
|
| 581 |
+
-------
|
| 582 |
+
eng_normed : np.ndarray
|
| 583 |
+
Copy of eng with lufs and peak_lufs shifted by gain_db.
|
| 584 |
+
gain_db : float
|
| 585 |
+
Gain applied (always <= 0.0).
|
| 586 |
+
"""
|
| 587 |
+
try:
|
| 588 |
+
lufs_idx = ENG_DIMS.index("lufs")
|
| 589 |
+
peak_idx = ENG_DIMS.index("peak_lufs")
|
| 590 |
+
except ValueError as exc:
|
| 591 |
+
raise ValueError(
|
| 592 |
+
f"apply_streaming_normalization: required dimension not found in ENG_DIMS: {exc}"
|
| 593 |
+
) from exc
|
| 594 |
+
|
| 595 |
+
# True peak cap: only active when true_peak_dbfs is provided and finite.
|
| 596 |
+
# When true_peak > -1.0 dBFS (intersample peak above limiter ceiling),
|
| 597 |
+
# tp_headroom is negative, further restricting the gain so the normalized
|
| 598 |
+
# true peak lands at -1.0 dBFS. When true_peak <= -1.0 dBFS, tp_headroom
|
| 599 |
+
# is non-negative and the existing 0.0 cap is the binding constraint.
|
| 600 |
+
tp_headroom = (
|
| 601 |
+
(-1.0 - true_peak_dbfs)
|
| 602 |
+
if (true_peak_dbfs is not None and np.isfinite(true_peak_dbfs))
|
| 603 |
+
else 0.0
|
| 604 |
+
)
|
| 605 |
+
gain_db = min(target_lufs - eng[lufs_idx], tp_headroom, 0.0)
|
| 606 |
+
out = eng.copy()
|
| 607 |
+
out[lufs_idx] += gain_db
|
| 608 |
+
out[peak_idx] += gain_db
|
| 609 |
+
return out, gain_db
|
| 610 |
+
|
| 611 |
+
|
| 612 |
+
def _compute_drum_bands(drum_mono: np.ndarray, mix_mono: np.ndarray, sr: int) -> tuple:
|
| 613 |
+
"""
|
| 614 |
+
Returns (kick_dom, cymbal_presence, hihat_presence).
|
| 615 |
+
|
| 616 |
+
kick_dom β dominance ratio (unchanged from v5):
|
| 617 |
+
RMS(drum_stem, 40β120 Hz) / RMS(mix, 40β120 Hz)
|
| 618 |
+
cymbal_presence β HPSS sustained fraction Γ band prominence in 4β10 kHz [0,1]
|
| 619 |
+
hihat_presence β onset density of HPSS percussive 8β14 kHz component [0,1]
|
| 620 |
+
|
| 621 |
+
WHY HPSS INSTEAD OF DOMINANCE RATIO FOR CYMBAL / HI-HAT (v6):
|
| 622 |
+
|
| 623 |
+
The v5 formula drum_cymbal_presence = RMS(drum_8-16kHz) / RMS(mix_8-16kHz)
|
| 624 |
+
conflated hi-hats and crashes and failed in mixed-source tracks. When a bright
|
| 625 |
+
guitar or synth pad adds energy at 8-16 kHz alongside real drum content, the
|
| 626 |
+
mix denominator inflates while the drum numerator is unchanged β the ratio drops
|
| 627 |
+
below the lane mean even with cymbals audibly present throughout the track.
|
| 628 |
+
|
| 629 |
+
HPSS (Harmonic-Percussive Source Separation, librosa.decompose.hpss) applies
|
| 630 |
+
a horizontal median filter to the magnitude spectrogram to extract sustained
|
| 631 |
+
tonal content (H) and a vertical median filter for transient broadband content (P):
|
| 632 |
+
|
| 633 |
+
H (harmonic/sustained): crash ring-out, ride shimmer, guitar chord sustain.
|
| 634 |
+
P (percussive/transient): hi-hat clicks, kick/snare attacks.
|
| 635 |
+
|
| 636 |
+
The H component is not affected by other instruments' level in the full mix β
|
| 637 |
+
it measures what is sustained within the drum stem's own spectrogram. A crash
|
| 638 |
+
ring-out is always captured in H regardless of guitar/synth in the full mix.
|
| 639 |
+
|
| 640 |
+
CYMBAL (crash/ride): measured via sustained fraction Γ band prominence.
|
| 641 |
+
sustained_frac = H_energy(4-10kHz) / total_energy(4-10kHz)
|
| 642 |
+
β high when crash ring-out dominates 4-10kHz drum content
|
| 643 |
+
β lower for snare-only (snare ring has less sustained relative energy in band)
|
| 644 |
+
band_prom = RMS(mag_4-10kHz) / RMS(mag_all_freqs)
|
| 645 |
+
β scales by how much 4-10kHz energy the drum stem actually carries
|
| 646 |
+
β near-silent drum stem (no drums) β band_prom β 0 β product β 0
|
| 647 |
+
Combined: cymbal_presence = (sustained_frac Γ band_prom) / CYMBAL_SAT
|
| 648 |
+
|
| 649 |
+
HI-HAT: measured via onset density of percussive 8-14 kHz signal.
|
| 650 |
+
1. Apply soft percussive mask P/(mag+EPS) to complex STFT D.
|
| 651 |
+
2. Zero all frequency bins outside 8-14 kHz.
|
| 652 |
+
3. Reconstruct time-domain hi-hat signal via iSTFT.
|
| 653 |
+
4. Run librosa onset detection on reconstructed signal.
|
| 654 |
+
5. onset_rate (onsets/sec) / HIHAT_ONSET_SAT β [0,1].
|
| 655 |
+
|
| 656 |
+
Guitar chord rings at 8-14 kHz are sustained β H component β soft_p low
|
| 657 |
+
for those bins β soft-masked out. Guitar staccato transients at 8-14 kHz
|
| 658 |
+
are much weaker than real hi-hat transients β below onset_detect threshold.
|
| 659 |
+
"""
|
| 660 |
+
# ββ Kick dominance (unchanged from v5) ββββββββββββββββββββββββββββββββββββ
|
| 661 |
+
kick_mix = _band_rms_abs(mix_mono, sr, DRUM_KICK_FMIN, DRUM_KICK_FMAX)
|
| 662 |
+
kick_drum = _band_rms_abs(drum_mono, sr, DRUM_KICK_FMIN, DRUM_KICK_FMAX)
|
| 663 |
+
kick_dom = float(min(kick_drum / (kick_mix + EPS), 1.0)) if kick_mix >= EPS else 0.0
|
| 664 |
+
|
| 665 |
+
# ββ STFT + HPSS on drum stem ββββββββββββββββββββββββββββββββββββββββββββββ
|
| 666 |
+
n_fft = 2048
|
| 667 |
+
hop = 512
|
| 668 |
+
D = librosa.stft(drum_mono, n_fft=n_fft, hop_length=hop) # complex (1025, n_frames)
|
| 669 |
+
mag = np.abs(D) # magnitude spectrogram
|
| 670 |
+
H, P = librosa.decompose.hpss(mag, kernel_size=31, power=2.0) # H=sustained, P=transient
|
| 671 |
+
freqs = librosa.fft_frequencies(sr=sr, n_fft=n_fft) # shape (1025,)
|
| 672 |
+
|
| 673 |
+
# ββ Cymbal presence: HPSS sustained energy in 4β10 kHz βββββββββββββββββββ
|
| 674 |
+
cymbal_mask = (freqs >= CYMBAL_BAND_FMIN) & (freqs <= CYMBAL_BAND_FMAX)
|
| 675 |
+
H_cym = H[cymbal_mask, :] # sustained component in cymbal band
|
| 676 |
+
mag_cym = mag[cymbal_mask, :] # total magnitude in cymbal band
|
| 677 |
+
|
| 678 |
+
H_cym_energy = float(np.mean(H_cym ** 2))
|
| 679 |
+
band_energy = float(np.mean(mag_cym ** 2)) + EPS
|
| 680 |
+
sustained_frac = H_cym_energy / band_energy # fraction of cymbal-band energy that is sustained
|
| 681 |
+
|
| 682 |
+
band_rms = float(np.sqrt(np.mean(mag_cym ** 2)))
|
| 683 |
+
total_mag_rms = float(np.sqrt(np.mean(mag ** 2))) + EPS
|
| 684 |
+
band_prom = band_rms / total_mag_rms # cymbal band's prominence in overall drum stem
|
| 685 |
+
|
| 686 |
+
cymbal_presence = float(min((sustained_frac * band_prom) / CYMBAL_SAT, 1.0))
|
| 687 |
+
|
| 688 |
+
# ββ Hi-hat presence: onset density of percussive 8β14 kHz component ββββββ
|
| 689 |
+
hihat_mask = (freqs >= HIHAT_BAND_FMIN) & (freqs <= HIHAT_BAND_FMAX)
|
| 690 |
+
# Soft-mask: amplify percussive content, suppress sustained content per bin.
|
| 691 |
+
# soft_p[f,t] = P[f,t] / (mag[f,t] + EPS) β [0,1] β how percussive each bin is.
|
| 692 |
+
soft_p = P / (mag + EPS)
|
| 693 |
+
D_hihat = D * soft_p # complex STFT weighted toward percussive content
|
| 694 |
+
D_hihat[~hihat_mask, :] = 0.0 # zero non-hihat frequencies
|
| 695 |
+
# iSTFT reconstructs time-domain signal containing only percussive 8-14 kHz content.
|
| 696 |
+
hihat_sig = librosa.istft(D_hihat, hop_length=hop, length=len(drum_mono))
|
| 697 |
+
|
| 698 |
+
oenv = librosa.onset.onset_strength(y=hihat_sig, sr=sr, hop_length=hop)
|
| 699 |
+
onsets = librosa.onset.onset_detect(onset_envelope=oenv, sr=sr, hop_length=hop)
|
| 700 |
+
duration = len(drum_mono) / sr
|
| 701 |
+
onset_rate = len(onsets) / max(duration, 1.0)
|
| 702 |
+
hihat_presence = float(min(onset_rate / HIHAT_ONSET_SAT, 1.0))
|
| 703 |
+
|
| 704 |
+
return kick_dom, cymbal_presence, hihat_presence
|
| 705 |
+
|
| 706 |
+
|
| 707 |
+
def _compute_guitar_dims(guitar_mono: np.ndarray, sr: int) -> tuple:
|
| 708 |
+
"""
|
| 709 |
+
Returns (egtr_presence, picking_density, mid_saturation).
|
| 710 |
+
All values in [0, 1].
|
| 711 |
+
|
| 712 |
+
egtr_presence β composite [0,1] electric guitar detection score:
|
| 713 |
+
EGTR_PICK_WEIGHT Γ picking_density
|
| 714 |
+
+ EGTR_FLAT_WEIGHT Γ mid_saturation
|
| 715 |
+
|
| 716 |
+
picking_density β onset density of the HPSS percussive component in
|
| 717 |
+
200β5000 Hz, normalized to EGTR_PICK_ONSET_SAT.
|
| 718 |
+
Detects pick/strum attack events per second.
|
| 719 |
+
Electric guitar: 2β6 onsets/sec. Sustained pads: 0β0.5.
|
| 720 |
+
Piano also produces picking onsets; the mid_saturation
|
| 721 |
+
gate separates piano (low flatness) from guitar (higher).
|
| 722 |
+
|
| 723 |
+
mid_saturation β spectral flatness of the guitar stem in 200β5000 Hz,
|
| 724 |
+
normalized to EGTR_FLATNESS_SAT.
|
| 725 |
+
Electric guitar (any gain): 0.05β0.40. Piano: 0.02β0.08.
|
| 726 |
+
Acoustic guitar (clean): 0.03β0.12.
|
| 727 |
+
Rewards harmonic saturation from magnetic pickups and
|
| 728 |
+
overdrive β the primary acoustic difference between
|
| 729 |
+
electric and acoustic guitar. Clean electric guitar
|
| 730 |
+
(e.g. Fender clean tone) scores low here; such tracks
|
| 731 |
+
still contribute via picking_density.
|
| 732 |
+
|
| 733 |
+
WHY HPSS ON GUITAR STEM (v8):
|
| 734 |
+
Even with htdemucs_6s providing a dedicated guitar stem, there is residual
|
| 735 |
+
bleed from other instruments. HPSS separates the percussive (transient
|
| 736 |
+
attack) component from the harmonic (sustained) component within the guitar
|
| 737 |
+
stem itself. Extracting the P component in 200-5000 Hz and counting onsets
|
| 738 |
+
isolates picking/strumming events even with stem bleed, because instrument
|
| 739 |
+
bleed (synths, pads, vocals) tends to be sustained (β H component) rather
|
| 740 |
+
than transient (β P component) in this frequency range.
|
| 741 |
+
|
| 742 |
+
ACOUSTIC VS ELECTRIC LIMITATION:
|
| 743 |
+
Clean acoustic and clean electric guitar will score similarly on both
|
| 744 |
+
sub-dimensions. The only reliable further discriminators without a
|
| 745 |
+
secondary model are:
|
| 746 |
+
1. Body resonance: acoustic guitar has a pronounced 150β400 Hz peak
|
| 747 |
+
in the guitar stem. This could be added as a third sub-dimension
|
| 748 |
+
in a future version.
|
| 749 |
+
2. CLAP embedding: already in the feature vector; the SVM implicitly
|
| 750 |
+
leverages CLAP's semantic understanding of guitar timbre. If your
|
| 751 |
+
lane refs consistently contain electric guitar and non_lane_refs
|
| 752 |
+
contain acoustic-only tracks, the SVM learns the residual difference
|
| 753 |
+
from CLAP + other dimensions even if egtr_presence alone cannot
|
| 754 |
+
fully separate them.
|
| 755 |
+
|
| 756 |
+
Intermediate values (picking_density, mid_saturation) are returned for
|
| 757 |
+
debug/tuning but are NOT added to ENG_DIMS β only egtr_presence and
|
| 758 |
+
egtr_level are scoreable dimensions, preserving the atomicity principle.
|
| 759 |
+
"""
|
| 760 |
+
if np.sqrt(np.mean(guitar_mono ** 2)) < EPS:
|
| 761 |
+
# Silent guitar stem β no guitar in the track.
|
| 762 |
+
return 0.0, 0.0, 0.0
|
| 763 |
+
|
| 764 |
+
n_fft = 2048
|
| 765 |
+
hop = 512
|
| 766 |
+
D = librosa.stft(guitar_mono, n_fft=n_fft, hop_length=hop)
|
| 767 |
+
mag = np.abs(D)
|
| 768 |
+
H, P = librosa.decompose.hpss(mag, kernel_size=31, power=2.0)
|
| 769 |
+
freqs = librosa.fft_frequencies(sr=sr, n_fft=n_fft)
|
| 770 |
+
mid_mask = (freqs >= EGTR_MID_FMIN) & (freqs <= EGTR_MID_FMAX)
|
| 771 |
+
|
| 772 |
+
# ββ Picking density: onset rate of percussive mid-band content ββββββββββββ
|
| 773 |
+
# Soft-mask the complex STFT toward percussive content, isolate mid band.
|
| 774 |
+
soft_p = P / (mag + EPS) # per-bin percussiveness score [0,1]
|
| 775 |
+
D_pick = D * soft_p # complex STFT weighted toward transients
|
| 776 |
+
D_pick[~mid_mask, :] = 0.0 # zero bins outside guitar mid band
|
| 777 |
+
pick_sig = librosa.istft(D_pick, hop_length=hop, length=len(guitar_mono))
|
| 778 |
+
oenv = librosa.onset.onset_strength(y=pick_sig, sr=sr, hop_length=hop)
|
| 779 |
+
onsets = librosa.onset.onset_detect(onset_envelope=oenv, sr=sr, hop_length=hop)
|
| 780 |
+
duration = len(guitar_mono) / sr
|
| 781 |
+
onset_rate = len(onsets) / max(duration, 1.0)
|
| 782 |
+
picking_density = float(min(onset_rate / EGTR_PICK_ONSET_SAT, 1.0))
|
| 783 |
+
|
| 784 |
+
# ββ Mid-band spectral flatness: harmonic saturation from pickups/overdrive β
|
| 785 |
+
# Flatness = geometric_mean / arithmetic_mean of magnitude spectrum.
|
| 786 |
+
# Ranges [0, 1]: 0 = perfectly tonal (sine-like), 1 = flat noise.
|
| 787 |
+
# Electric guitar pickups and overdrive add intermodulation products that
|
| 788 |
+
# raise flatness compared to clean acoustic guitar or piano.
|
| 789 |
+
mag_mid = mag[mid_mask, :]
|
| 790 |
+
if mag_mid.size == 0 or mag_mid.shape[0] == 0:
|
| 791 |
+
mid_saturation = 0.0
|
| 792 |
+
else:
|
| 793 |
+
geo_mean = np.exp(np.mean(np.log(mag_mid + EPS), axis=0)) # per-frame geo mean
|
| 794 |
+
arith_mean = np.mean(mag_mid, axis=0) + EPS # per-frame arith mean
|
| 795 |
+
frame_flat = geo_mean / arith_mean # flatness [0,1] per frame
|
| 796 |
+
raw_flatness = float(np.mean(frame_flat))
|
| 797 |
+
mid_saturation = float(min(raw_flatness / EGTR_FLATNESS_SAT, 1.0))
|
| 798 |
+
|
| 799 |
+
egtr_presence = float(
|
| 800 |
+
EGTR_PICK_WEIGHT * picking_density +
|
| 801 |
+
EGTR_FLAT_WEIGHT * mid_saturation
|
| 802 |
+
)
|
| 803 |
+
|
| 804 |
+
return egtr_presence, picking_density, mid_saturation
|
| 805 |
+
|
| 806 |
+
|
| 807 |
+
def extract_mir_features(path):
|
| 808 |
+
"""
|
| 809 |
+
Returns (l3_vec, eng_vec, true_peak_dbfs).
|
| 810 |
+
|
| 811 |
+
eng_vec is a 32-element array whose indices correspond to ENG_DIMS.
|
| 812 |
+
Indices 0β25 are unchanged from cache version 3.
|
| 813 |
+
Indices 26β29 are drum sub-dimensions (v4βv6, unchanged in v8):
|
| 814 |
+
26 drum_kick_presence β kick dominance ratio (v5, unchanged in v6)
|
| 815 |
+
27 drum_cymbal_presence β HPSS sustained fraction Γ band prom in 4β10 kHz (v6)
|
| 816 |
+
28 drum_confidence β 0.55Γkick + 0.30Γhihat + 0.15Γcymbal (v6)
|
| 817 |
+
29 hihat_presence β onset density of percussive 8β14 kHz (v6 NEW)
|
| 818 |
+
Indices 30β31 are electric guitar dimensions (v8 NEW):
|
| 819 |
+
30 egtr_presence β composite guitar detection score [0,1]
|
| 820 |
+
31 egtr_level β egtr_presence Γ (guitar_rms / total_rms)
|
| 821 |
+
|
| 822 |
+
drum_punch (index 2) is gated by drum_confidence:
|
| 823 |
+
drum_punch = crest_factor(drum_stem) Γ drum_confidence
|
| 824 |
+
|
| 825 |
+
v8 changes vs v7:
|
| 826 |
+
htdemucs_6s: model switched from htdemucs (4-stem) to htdemucs_6s (6-stem).
|
| 827 |
+
New stems: guitar (_STEM_GUITAR=4), piano (_STEM_PIANO=5).
|
| 828 |
+
other_prominence (idx 12) now reflects only synths/pads/strings β
|
| 829 |
+
guitar and piano are no longer blended into the other stem.
|
| 830 |
+
total_rms: now includes guitar_rms + piano_rms (previously only 4 stems).
|
| 831 |
+
This makes all stem-share ratios (drum_prominence, bass_prominence,
|
| 832 |
+
other_prominence, vocal_level) slightly different from v7.
|
| 833 |
+
egtr_presence (idx 30): HPSS-based picking density + mid-band spectral
|
| 834 |
+
flatness on the dedicated guitar stem. See _compute_guitar_dims().
|
| 835 |
+
egtr_level (idx 31): egtr_presence Γ (guitar_rms / total_rms).
|
| 836 |
+
Scales presence by the guitar stem's share of the total mix RMS.
|
| 837 |
+
A guitar that is present but buried low in the mix scores lower than
|
| 838 |
+
one that is both detectable and prominent.
|
| 839 |
+
eng_vec now has 32 elements. All v7 cache entries are incompatible.
|
| 840 |
+
|
| 841 |
+
true_peak_dbfs is the ITU-R BS.1775-2 true peak level of the full mix
|
| 842 |
+
(4Γ oversampled, in dBFS). Returned so the caller can enforce the -1.0 dBFS
|
| 843 |
+
true peak ceiling in apply_streaming_normalization() correctly.
|
| 844 |
+
|
| 845 |
+
Expected outcomes by source type (approximate):
|
| 846 |
+
Distorted electric guitar prominent in mix:
|
| 847 |
+
egtr_presence β 0.55β0.95, egtr_level β 0.15β0.45
|
| 848 |
+
Clean electric guitar (Fender/Strat clean tone):
|
| 849 |
+
egtr_presence β 0.25β0.55, egtr_level β 0.05β0.25
|
| 850 |
+
Acoustic guitar only (no electric):
|
| 851 |
+
egtr_presence β 0.10β0.35, egtr_level β 0.02β0.15
|
| 852 |
+
Piano-led track (no guitar):
|
| 853 |
+
egtr_presence β 0.05β0.20, egtr_level β 0.01β0.08
|
| 854 |
+
Pad/synth-led track (no guitar):
|
| 855 |
+
egtr_presence β 0.00β0.15, egtr_level β 0.00β0.05
|
| 856 |
+
"""
|
| 857 |
+
y, sr = librosa.load(path, sr=44100, mono=True)
|
| 858 |
+
y_stereo, _ = librosa.load(path, sr=sr, mono=False)
|
| 859 |
+
if y_stereo.ndim == 1: # guard: mono input
|
| 860 |
+
y_stereo = np.stack([y_stereo, y_stereo])
|
| 861 |
+
emb_l3, _ = openl3.get_audio_embedding(
|
| 862 |
+
y, sr, content_type="music", embedding_size=512, verbose=False
|
| 863 |
+
)
|
| 864 |
+
l3_vec = np.mean(emb_l3, axis=0)
|
| 865 |
+
src = get_stems(path) # shape: (6, 2, n_samples) β stereo stems at 44100 Hz
|
| 866 |
+
|
| 867 |
+
# ββ Stem RMS values βββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 868 |
+
drum_rms = np.sqrt(np.mean(src[_STEM_DRUMS] **2))
|
| 869 |
+
bass_rms = np.sqrt(np.mean(src[_STEM_BASS] **2))
|
| 870 |
+
other_rms = np.sqrt(np.mean(src[_STEM_OTHER] **2))
|
| 871 |
+
voc_rms = np.sqrt(np.mean(src[_STEM_VOCALS]**2))
|
| 872 |
+
guitar_rms = np.sqrt(np.mean(src[_STEM_GUITAR]**2))
|
| 873 |
+
piano_rms = np.sqrt(np.mean(src[_STEM_PIANO] **2))
|
| 874 |
+
# v8: total_rms includes all 6 stems for accurate mix-share ratios.
|
| 875 |
+
total_rms = drum_rms + bass_rms + other_rms + voc_rms + guitar_rms + piano_rms + EPS
|
| 876 |
+
|
| 877 |
+
# ββ Drum crest factor (raw, before gating) ββββββββββββββββββββββββββββββββ
|
| 878 |
+
drum_crest_raw = np.max(np.abs(src[_STEM_DRUMS])) / (drum_rms + EPS)
|
| 879 |
+
|
| 880 |
+
# ββ Drum sub-band analysis (v6, unchanged in v8) ββββββββββββββββββββββββββ
|
| 881 |
+
drum_mono = (src[_STEM_DRUMS][0] + src[_STEM_DRUMS][1]) / 2.0
|
| 882 |
+
|
| 883 |
+
drum_kick_pres, drum_cymbal_pres, hihat_pres = _compute_drum_bands(drum_mono, y, sr)
|
| 884 |
+
|
| 885 |
+
# drum_confidence: weighted sum of three [0,1] drum indicators.
|
| 886 |
+
kick_conf = min(drum_kick_pres / DRUM_KICK_SAT, 1.0)
|
| 887 |
+
hihat_conf = hihat_pres # already in [0, 1]
|
| 888 |
+
cymbal_conf = drum_cymbal_pres # already in [0, 1]
|
| 889 |
+
drum_conf = float(
|
| 890 |
+
DRUM_KICK_WEIGHT * kick_conf +
|
| 891 |
+
DRUM_HIHAT_WEIGHT * hihat_conf +
|
| 892 |
+
DRUM_CYMBAL_WEIGHT * cymbal_conf
|
| 893 |
+
)
|
| 894 |
+
|
| 895 |
+
# Gate drum_punch by confidence: suppresses false positives from guitar bleed.
|
| 896 |
+
drum_punch_val = drum_crest_raw * drum_conf
|
| 897 |
+
|
| 898 |
+
# ββ Bass crest factor βββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 899 |
+
bass_tightness_val = np.max(np.abs(src[_STEM_BASS])) / (bass_rms + EPS)
|
| 900 |
+
|
| 901 |
+
# ββ Mix-presence ratios βββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 902 |
+
drum_prom = drum_rms / total_rms
|
| 903 |
+
bass_prom = bass_rms / total_rms
|
| 904 |
+
other_prom = other_rms / total_rms
|
| 905 |
+
voc_level = voc_rms / total_rms
|
| 906 |
+
|
| 907 |
+
# ββ Vocal sub-dimensions ββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 908 |
+
voc_mono = (src[_STEM_VOCALS][0] + src[_STEM_VOCALS][1]) / 2.0
|
| 909 |
+
voc_rms_frames = librosa.feature.rms(
|
| 910 |
+
y=voc_mono, frame_length=2048, hop_length=512
|
| 911 |
+
)[0]
|
| 912 |
+
voc_presence = float(np.mean(voc_rms_frames > VOCAL_ACTIVITY_THRESHOLD))
|
| 913 |
+
voc_brightness = float(np.mean(
|
| 914 |
+
librosa.feature.spectral_centroid(y=voc_mono, sr=sr)
|
| 915 |
+
))
|
| 916 |
+
|
| 917 |
+
# ββ Electric guitar sub-dimensions (v8 NEW) βββββββββββββββββββββββββββββββ
|
| 918 |
+
guitar_mono = (src[_STEM_GUITAR][0] + src[_STEM_GUITAR][1]) / 2.0
|
| 919 |
+
egtr_pres, _picking, _flatness = _compute_guitar_dims(guitar_mono, sr)
|
| 920 |
+
# egtr_level: scale presence by the guitar's share of total mix RMS.
|
| 921 |
+
# Rewards tracks where guitar is both detectable AND prominent in the mix.
|
| 922 |
+
egtr_level_val = float(egtr_pres * (guitar_rms / total_rms))
|
| 923 |
+
|
| 924 |
+
# ββ Mid-side stereo width βββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 925 |
+
mid, side = (y_stereo[0] + y_stereo[1]) / 2, (y_stereo[0] - y_stereo[1]) / 2
|
| 926 |
+
ms_ratio = (np.sqrt(np.mean(side**2)) /
|
| 927 |
+
(np.sqrt(np.mean(mid**2)) + np.sqrt(np.mean(side**2)) + EPS))
|
| 928 |
+
|
| 929 |
+
# ββ Short-term loudness (K-weighted, BS.1770 β no gating) ββββββββββββββββ
|
| 930 |
+
# Uses the same K-weighting filter as integrated LUFS. window=3s, hop=1s
|
| 931 |
+
# matches the original librosa.feature.rms() block framing.
|
| 932 |
+
st_lufs = _compute_short_term_lufs_array(y_stereo, sr, window_s=3.0, hop_s=1.0)
|
| 933 |
+
|
| 934 |
+
# ββ Clipping βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 935 |
+
c_events, c_total, c_ratio, c_max, c_mean = _measure_clipping(y)
|
| 936 |
+
|
| 937 |
+
# ββ Assemble eng_vec β must match ENG_DIMS order exactly βββββββββββββββββ
|
| 938 |
+
eng_vec = np.array([
|
| 939 |
+
_compute_integrated_lufs(y_stereo, sr), # 0 lufs (ITU-R BS.1770-4 β K-weighted, gated)
|
| 940 |
+
np.max(np.abs(y)) / (np.sqrt(np.mean(y**2)) + EPS), # 1 crest_factor
|
| 941 |
+
drum_punch_val, # 2 drum_punch (gated)
|
| 942 |
+
drum_prom, # 3 drum_prominence
|
| 943 |
+
ms_ratio, # 4 stereo_width
|
| 944 |
+
librosa.feature.spectral_centroid(y=y, sr=sr).mean(), # 5 brightness
|
| 945 |
+
entropy(np.mean(librosa.feature.chroma_cqt(y=y, sr=sr), axis=1)), # 6 harmonic_complexity
|
| 946 |
+
c_events, # 7 clip_num_events
|
| 947 |
+
c_total, # 8 clip_total
|
| 948 |
+
c_ratio, # 9 clip_ratio
|
| 949 |
+
c_max, # 10 clip_max_run
|
| 950 |
+
c_mean, # 11 clip_mean_run
|
| 951 |
+
other_prom, # 12 other_prominence
|
| 952 |
+
voc_level, # 13 vocal_level
|
| 953 |
+
voc_presence, # 14 vocal_presence
|
| 954 |
+
voc_brightness, # 15 vocal_brightness
|
| 955 |
+
np.max(st_lufs) - np.median(st_lufs), # 16 chorus_lift
|
| 956 |
+
np.mean(librosa.feature.zero_crossing_rate(y)), # 17 crispness
|
| 957 |
+
np.mean(librosa.feature.spectral_flatness(y=y)), # 18 clarity
|
| 958 |
+
len(y) / sr, # 19 length_s
|
| 959 |
+
np.std(st_lufs), # 20 lufs_variation
|
| 960 |
+
np.max(st_lufs), # 21 peak_lufs
|
| 961 |
+
np.mean(librosa.feature.spectral_rolloff(y=y, sr=sr)), # 22 rolloff
|
| 962 |
+
bass_tightness_val, # 23 bass_tightness
|
| 963 |
+
bass_prom, # 24 bass_prominence
|
| 964 |
+
np.nan_to_num(np.corrcoef(y_stereo[0], y_stereo[1])[0, 1]), # 25 phase_corr
|
| 965 |
+
drum_kick_pres, # 26 drum_kick_presence
|
| 966 |
+
drum_cymbal_pres, # 27 drum_cymbal_presence (v6)
|
| 967 |
+
drum_conf, # 28 drum_confidence (v6)
|
| 968 |
+
hihat_pres, # 29 hihat_presence (v6)
|
| 969 |
+
egtr_pres, # 30 egtr_presence (v8 NEW)
|
| 970 |
+
egtr_level_val, # 31 egtr_level (v8 NEW)
|
| 971 |
+
])
|
| 972 |
+
|
| 973 |
+
# ββ True peak (BS.1775-2, 4Γ oversampled) ββββββββββββββββββββββββββββββββ
|
| 974 |
+
# Returned as third element so the modal worker / analyze_submissions.py
|
| 975 |
+
# can enforce the -1.0 dBFS true peak ceiling in normalization simulation.
|
| 976 |
+
true_peak = _true_peak_dbfs(y_stereo)
|
| 977 |
+
|
| 978 |
+
return l3_vec, eng_vec, true_peak
|