def get_spectral_average_variance_entropy(self):
segments_stft = None
N = 2**10
stft = np.copy(self.stft)
# stft = AudioProcessing.rescale(self.stft,(0,N))
# stft = stft.astype(np.uint16)
for segment in self.segments:
start = int(float(segment[0]) / self.n_fft)
stop = int(float(segment[1]) / self.n_fft)
if segments_stft is None:
segments_stft = stft[:, start:stop]
else:
segments_stft = np.concatenate(
(segments_stft, stft[:, start:stop]), axis=1)
average_spectra = np.mean(segments_stft, axis=1)
var_spectra = np.var(segments_stft, axis=1)
N = 2**8
average_spectra = AudioProcessing.rescale(average_spectra, (0, N))
average_spectra = average_spectra.astype(np.uint8)
var_spectra = AudioProcessing.rescale(var_spectra, (0, N))
var_spectra = var_spectra.astype(np.uint8)
avg_pdf, bins = AudioProcessing.get_histogram(average_spectra,
bins=np.arange(0, 255))
var_pdf, bins = AudioProcessing.get_histogram(var_spectra,
bins=np.arange(0, 255))
avg_pdf = avg_pdf[np.nonzero(avg_pdf)]
var_pdf = var_pdf[np.nonzero(var_pdf)]
average_spectrum_entropy = AudioProcessing.get_entropy(
avg_pdf) / np.log2(N)
variance_spectrum_entropy = AudioProcessing.get_entropy(
var_pdf) / np.log2(N)
return average_spectrum_entropy, variance_spectrum_entropy
def get_spectral_maxima_entropy(self):
max_bins = []
for segment in self.segments:
start = int(float(segment[0]) / self.n_fft)
stop = int(float(segment[1]) / self.n_fft)
for i in range(start, stop + 1):
stft_column = self.stft[:, i]
max_bins.append(np.argmax(stft_column))
pdf, bins = AudioProcessing.get_histogram(max_bins,
bins=np.arange(
0, self.stft.shape[0]))
pdf = pdf[np.nonzero(pdf)]
spectral_max_entropy = AudioProcessing.get_entropy(pdf) / np.log2(
self.stft.shape[0])
return spectral_max_entropy