def __new__(cls, spectrogram, filterbank=PCP, num_classes=PCP.CLASSES,
fmin=PCP.FMIN, fmax=PCP.FMAX, fref=A4, **kwargs):
# check spectrogram type
if not isinstance(spectrogram, Spectrogram):
spectrogram = Spectrogram(spectrogram, **kwargs)
# the spectrogram must not be filtered
if spectrogram.filterbank is not None:
import warnings
warnings.warn('Spectrogram should not be filtered.')
# reference frequency for the filterbank
if fref is None:
fref = spectrogram.tuning_frequency()
# set filterbank
if issubclass(filterbank, Filterbank):
filterbank = filterbank(spectrogram.bin_frequencies,
num_classes=num_classes, fmin=fmin,
fmax=fmax, fref=fref)
if not isinstance(filterbank, Filterbank):
raise ValueError('not a Filterbank type or instance: %s' %
filterbank)
# filter the spectrogram
data = np.dot(spectrogram, filterbank)
# cast as PitchClassProfile
obj = np.asarray(data).view(cls)
# save additional attributes
obj.filterbank = filterbank
obj.spectrogram = spectrogram
# return the object
return obj
def __new__(cls, spectrogram, filterbank=PCP, num_classes=PCP.CLASSES,
fmin=PCP.FMIN, fmax=PCP.FMAX, fref=A4, **kwargs):
# check spectrogram type
if not isinstance(spectrogram, Spectrogram):
spectrogram = Spectrogram(spectrogram, **kwargs)
# spectrogram should not be filtered
if hasattr(spectrogram, 'filterbank'):
warnings.warn('Spectrogram should not be filtered.',
RuntimeWarning)
# reference frequency for the filterbank
if fref is None:
fref = spectrogram.tuning_frequency()
# set filterbank
if issubclass(filterbank, Filterbank):
filterbank = filterbank(spectrogram.bin_frequencies,
num_classes=num_classes, fmin=fmin,
fmax=fmax, fref=fref)
if not isinstance(filterbank, Filterbank):
raise ValueError('not a Filterbank type or instance: %s' %
filterbank)
# filter the spectrogram
data = np.dot(spectrogram, filterbank)
# cast as PitchClassProfile
obj = np.asarray(data).view(cls)
# save additional attributes
obj.filterbank = filterbank
obj.spectrogram = spectrogram
# return the object
return obj
def getPCPHistogram(filename, fs=8192, show=False):
res = {}
sig = Signal(filename, num_channels=1)
fsig = FramedSignal(sig, frame_size=fs)
stft = ShortTimeFourierTransform(fsig)
spec = Spectrogram(stft)
chroma = PitchClassProfile(spec, num_classes=12)
hist = [0 for i in range(12)]
hist_f = [0 for i in range(12)]
for f in range(len(chroma)):
wf = chroma[f]
hist = map(sum, zip(hist, wf))
f = flatness(wf)
hist_f = map(sum, zip(hist_f, [w * f for w in wf]))
s = sum(hist)
hist = map(lambda x: x / s, hist)
C_hist = [hist[i - 9] for i in range(12)]
res['standard'] = C_hist
s_f = sum(hist_f)
hist_f = map(lambda x: x / s_f, hist_f)
C_hist_f = [hist_f[i - 9] for i in range(12)]
res['standard_f'] = C_hist_f
hpss = HarmonicPercussiveSourceSeparation()
h, _ = hpss.process(spec)
chroma = PitchClassProfile(h, num_classes=12)
hist = [0 for i in range(12)]
hist_f = [0 for i in range(12)]
for f in range(len(chroma)):
wf = chroma[f]
hist = map(sum, zip(hist, wf))
f = flatness(wf)
hist_f = map(sum, zip(hist_f, [w * f for w in wf]))
s = sum(hist)
hist = map(lambda x: x / s, hist)
C_hist = [hist[i - 9] for i in range(12)]
res['hpss'] = C_hist
s_f = sum(hist_f)
hist_f = map(lambda x: x / s_f, hist_f)
C_hist_f = [hist_f[i - 9] for i in range(12)]
res['hpss_f'] = C_hist_f
dcp = DeepChromaProcessor()
deepchroma = dcp(filename)
hist = [0 for i in range(12)]
hist_f = [0 for i in range(12)]
for f in range(len(deepchroma)):
wf = deepchroma[f]
hist = map(sum, zip(hist, wf))
f = flatness(wf)
hist_f = map(sum, zip(hist_f, [w * f for w in wf]))
s = sum(hist)
hist = map(lambda x: x / s, hist)
res['deep'] = hist
s_f = sum(hist_f)
hist_f = map(lambda x: x / s_f, hist_f)
res['deep_f'] = hist_f
if show:
plt.subplot(131)
plt.barh(range(12), res['standard'])
plt.subplot(132)
plt.barh(range(12), res['hpss'])
plt.subplot(133)
plt.barh(range(12), res['deep'])
plt.show()
return res
from os.path import join as pj
from . import AUDIO_PATH, ACTIVATIONS_PATH
from madmom.audio.signal import SignalProcessor, FramedSignalProcessor
from madmom.audio.filters import LogarithmicFilterbank
from madmom.audio.stft import ShortTimeFourierTransformProcessor
from madmom.audio.spectrogram import (Spectrogram, SpectrogramProcessor,
FilteredSpectrogramProcessor,
LogarithmicFilteredSpectrogram,
LogarithmicSpectrogramProcessor)
from madmom.features import Activations
from madmom.features.onsets import *
sample_file = pj(AUDIO_PATH, 'sample.wav')
sample_spec = Spectrogram(sample_file, circular_shift=True)
sample_log_filt_spec = LogarithmicFilteredSpectrogram(
sample_spec, num_bands=24, mul=1, add=1)
sample_cnn_act = Activations(pj(ACTIVATIONS_PATH, 'sample.onsets_cnn.npz'))
sample_rnn_act = Activations(pj(ACTIVATIONS_PATH, 'sample.onsets_rnn.npz'))
sample_brnn_act = Activations(pj(ACTIVATIONS_PATH, 'sample.onsets_brnn.npz'))
sample_superflux_act = Activations(pj(ACTIVATIONS_PATH,
'sample.super_flux.npz'))
class TestHighFrequencyContentFunction(unittest.TestCase):
def test_values(self):
odf = high_frequency_content(sample_log_filt_spec)
self.assertTrue(np.allclose(odf[:6], [8.97001563, 9.36399107,
8.64144536, 8.34977449,