def plot_mfcc_pca(recording, speaker):
""" Performs a Principal Components decomposition on the set of Mel-Frequency Cepstral Coefficients extracted
from the selected speaker's vocalizations.
:param recording: A Recording object to analyze
:param speaker: The LENA speaker category to analyze
"""
index, _, _ = recording.filter_speaker(speaker)
starts, ends, mfccs = speaker_mfccs(recording, speaker)
pca = PCA(n_components=2)
x = pca.fit_transform(mfccs)
fig, ax = pyplot.subplots()
comp1_label = 'Comp 1 ({0:.2f}% Variance)'.format(100 * pca.explained_variance_ratio_[0])
comp2_label = 'Comp 2 ({0:.2f}% Variance)'.format(100 * pca.explained_variance_ratio_[1])
def fmt(i, x, y):
import subprocess
command = 'start {root}/{subject_id}/{speaker}/{voc}.wav'.format(
root=recording.root, subject_id=recording.recording_id, speaker=speaker, voc=i)
print(command)
subprocess.call(command, shell=True)
return 'Voc: {i:.0f}\nx: {x:0.2f}\ny: {y:0.2f}'.format(i=i, x=x, y=y)
cursor = FollowDotCursor(ax, index, x[:,0], x[:,1], formatter=fmt, tolerance=20)
pyplot.scatter(x[:,0], x[:,1], c=starts, cmap=pyplot.cm.get_cmap('hot'))
pyplot.xlabel(comp1_label)
pyplot.ylabel(comp2_label)
pyplot.title('Principal Components of {0} MFCCs'.format(len(index)))
boxstyle='round,pad=0.5', fc='yellow', alpha=0.75),
arrowprops = dict(
arrowstyle='->', connectionstyle='arc3,rad=0'))
return annotation
def snap(self, x, y):
"""Return the value in self.tree closest to x, y."""
dist, idx = self.tree.query(self.scaled((x, y)), k=1, p=1)
try:
return self._index[idx], self._points[idx][0], self._points[idx][1]
except IndexError:
# IndexError: index out of bounds
return self._points[0]
if __name__ == "__main__":
recording = rec.Recording('E:/ivfcr', rec.Recording.ids[0])
index, _, _ = recording.filter_speaker('CHN')
starts, ends, mfccs = speaker_mfccs(recording, 'CHN')
ica = FastICA(n_components=2)
x = ica.fit_transform(mfccs)
fig, ax = pyplot.subplots()
comp1_label = 'Component 1'
comp2_label = 'Component 2'
cursor = FollowDotCursor(ax, index, x[:,0], x[:,1], formatter=fmt, tolerance=20)
pyplot.plot(x[:100,0], x[:100,1])
pyplot.xlabel(comp1_label)
pyplot.ylabel(comp2_label)
pyplot.title('Fast ICA of {0} MFCCs'.format(len(index)))
