Superflux onsets

This notebook demonstrates how to recover the Superflux onset detection algorithm of Boeck and Widmer, 2013 [1] from librosa.

This algorithm improves onset detection accuracy in the presence of vibrato.

# 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),

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.

plot superflux

Now we’ll compute the onset strength envelope and onset events using the librosa defaults.

And similarly with the superflux method

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)),

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[1].plot(frame_time, odf_sf, color='g', label='Superflux')
ax[1].vlines(onset_sf, 0, odf_sf.max(), color='r', label='Onsets')
plot superflux

Total running time of the script: (0 minutes 0.700 seconds)

Gallery generated by Sphinx-Gallery