1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
|
# coding: utf-8
"""
================
Superflux onsets
================
This notebook demonstrates how to recover the Superflux onset detection algorithm of
`Boeck and Widmer, 2013
<https://www.dafx.de/paper-archive/2013/papers/09.dafx2013_submission_12.pdf>`_ [1]_
from librosa.
This algorithm improves onset detection accuracy in the presence of vibrato.
.. [1] Böck, Sebastian, and Gerhard Widmer.
Maximum filter vibrato suppression for onset detection.
In Proc. of the 16th Int. Conf. on Digital Audio Effects (DAFx).
Maynooth, Ireland (Sept 2013), vol. 7, p. 4. 2013.
"""
# Code source: Brian McFee
# License: ISC
##################################################
# We'll need numpy and matplotlib for this example
import numpy as np
import matplotlib.pyplot as plt
import librosa
######################################################
# The method works fine for longer signals, but the
# results are harder to visualize.
y, sr = librosa.load(librosa.ex('trumpet', hq=True),
sr=44100)
####################################################
# These parameters are taken directly from the paper
n_fft = 1024
hop_length = int(librosa.time_to_samples(1./200, sr=sr))
lag = 2
n_mels = 138
fmin = 27.5
fmax = 16000.
max_size = 3
########################################################
# The paper uses a log-frequency representation, but for
# simplicity, we'll use a Mel spectrogram instead.
S = librosa.feature.melspectrogram(y=y, sr=sr, n_fft=n_fft,
hop_length=hop_length,
fmin=fmin,
fmax=fmax,
n_mels=n_mels)
fig, ax = plt.subplots()
librosa.display.specshow(librosa.power_to_db(S, ref=np.max),
y_axis='mel', x_axis='time', sr=sr,
hop_length=hop_length, fmin=fmin, fmax=fmax, ax=ax)
################################################################
# Now we'll compute the onset strength envelope and onset events
# using the librosa defaults.
odf_default = librosa.onset.onset_strength(y=y, sr=sr, hop_length=hop_length)
onset_default = librosa.onset.onset_detect(y=y, sr=sr, hop_length=hop_length,
units='time')
#########################################
# And similarly with the superflux method
odf_sf = librosa.onset.onset_strength(S=librosa.power_to_db(S, ref=np.max),
sr=sr,
hop_length=hop_length,
lag=lag, max_size=max_size)
onset_sf = librosa.onset.onset_detect(onset_envelope=odf_sf,
sr=sr,
hop_length=hop_length,
units='time')
######################################################################
# If you look carefully, the default onset detector (top sub-plot) has
# several false positives in high-vibrato regions, eg around 0.62s or
# 1.80s.
#
# The superflux method (middle plot) is less susceptible to vibrato, and
# does not detect onset events at those points.
# sphinx_gallery_thumbnail_number = 2
fig, ax = plt.subplots(nrows=3, sharex=True)
frame_time = librosa.frames_to_time(np.arange(len(odf_default)),
sr=sr,
hop_length=hop_length)
librosa.display.specshow(librosa.power_to_db(S, ref=np.max),
y_axis='mel', x_axis='time', sr=sr,
hop_length=hop_length, fmin=fmin, fmax=fmax, ax=ax[2])
ax[2].set(xlim=[0, 5.0])
ax[0].plot(frame_time, odf_default, label='Spectral flux')
ax[0].vlines(onset_default, 0, odf_default.max(), color='r', label='Onsets')
ax[0].legend()
ax[0].label_outer()
ax[1].plot(frame_time, odf_sf, color='g', label='Superflux')
ax[1].vlines(onset_sf, 0, odf_sf.max(), color='r', label='Onsets')
ax[1].legend()
ax[0].label_outer()
|
