def post_process(self):
'''
'''
aubio_res_id = 'aubio_pitch.pitch_confidence'
aubio_uuid = self.parents['aubio_pitch'].uuid()
aubio_results = self.process_pipe.results[aubio_uuid]
pitch_confidences = aubio_results[aubio_res_id].data
nb_frameDecision = int(self.decisionLen / self.wStep)
epsilon = numpy.spacing(pitch_confidences[0])
w = int(nb_frameDecision / 2)
is_mono = []
for i in range(w, len(pitch_confidences) - w, nb_frameDecision):
d = pitch_confidences[i - w:i + w]
conf_mean = numpy.mean(d)
conf_var = numpy.var(d + epsilon)
if self.monoLikelihood(conf_mean, conf_var) > self.polyLikelihood(
conf_mean, conf_var):
is_mono += [True]
else:
is_mono += [False]
conf = self.new_result(data_mode='value', time_mode='framewise')
conf = self.new_result(data_mode='value', time_mode='framewise')
conf.id_metadata.id += '.' + 'yin_confidence'
conf.id_metadata.name += ' ' + 'Yin Confidence'
conf.data_object.value = pitch_confidences
self.add_result(conf)
convert = {False: 0, True: 1}
label = {0: 'Poly', 1: 'Mono'}
segList = segmentFromValues(is_mono)
segs = self.new_result(data_mode='label', time_mode='segment')
segs.id_metadata.id += '.' + 'segments'
segs.id_metadata.name += ' ' + 'Segments'
segs.data_object.label_metadata.label = label
segs.data_object.label = [convert[s[2]] for s in segList]
segs.data_object.time = [(float(s[0] + 0.5) * self.decisionLen)
for s in segList]
segs.data_object.duration = [
(float(s[1] - s[0] + 1) * self.decisionLen) for s in segList
]
self.add_result(segs)
return
def post_process(self):
'''
'''
aubio_res_id = 'aubio_pitch.pitch_confidence'
aubio_uuid = self.parents['aubio_pitch'].uuid()
aubio_results = self.process_pipe.results[aubio_uuid]
pitch_confidences = aubio_results[aubio_res_id].data
nb_frameDecision = int(self.decisionLen / self.wStep)
epsilon = numpy.spacing(pitch_confidences[0])
w = int(nb_frameDecision/2)
is_mono = []
for i in range(w, len(pitch_confidences) - w, nb_frameDecision):
d = pitch_confidences[i - w:i + w]
conf_mean = numpy.mean(d)
conf_var = numpy.var(d + epsilon)
if self.monoLikelihood(conf_mean, conf_var) > self.polyLikelihood(conf_mean, conf_var):
is_mono += [True]
else:
is_mono += [False]
conf = self.new_result(data_mode='value', time_mode='framewise')
conf = self.new_result(data_mode='value', time_mode='framewise')
conf.id_metadata.id += '.' + 'yin_confidence'
conf.id_metadata.name += ' ' + 'Yin Confidence'
conf.data_object.value = pitch_confidences
self.add_result(conf)
convert = {False: 0, True: 1}
label = {0: 'Poly', 1: 'Mono'}
segList = segmentFromValues(is_mono)
segs = self.new_result(data_mode='label', time_mode='segment')
segs.id_metadata.id += '.' + 'segments'
segs.id_metadata.name += ' ' + 'Segments'
segs.data_object.label_metadata.label = label
segs.data_object.label = [convert[s[2]] for s in segList]
segs.data_object.time = [(float(s[0]+0.5) * self.decisionLen)
for s in segList]
segs.data_object.duration = [(float(s[1] - s[0]+1) * self.decisionLen)
for s in segList]
self.add_result(segs)
return
def post_process(self):
entropyValue = array(self.entropyValue)
w = self.modulLen * self.samplerate() / self.blocksize()
modulentropy = computeModulation(entropyValue, w, False)
confEntropy = array(modulentropy - self.threshold) / self.threshold
confEntropy[confEntropy > 1] = 1
conf = self.new_result(data_mode='value', time_mode='framewise')
conf.id_metadata.id += '.' + 'confidence'
conf.id_metadata.name += ' ' + 'Confidence'
conf.data_object.value = confEntropy
self.add_result(conf)
# Binary Entropy
binaryEntropy = modulentropy > self.threshold
binaryEntropy = binary_opening(binaryEntropy,
[1] * (self.smoothLen * 2))
convert = {False: 0, True: 1}
label = {0: 'NonSpeech', 1: 'Speech'}
segList = segmentFromValues(binaryEntropy)
segs = self.new_result(data_mode='label', time_mode='segment')
segs.id_metadata.id += '.' + 'segments'
segs.id_metadata.name += ' ' + 'Segments'
segs.data_object.label_metadata.label = label
segs.data_object.label = [convert[s[2]] for s in segList]
segs.data_object.time = [
(float(s[0]) * self.blocksize() / self.samplerate())
for s in segList
]
segs.data_object.duration = [
(float(s[1] - s[0] + 1) * self.blocksize() / self.samplerate())
for s in segList
]
self.add_result(segs)
return
def post_process(self):
entropyValue = array(self.entropyValue)
w = self.modulLen * self.samplerate() / self.blocksize()
modulentropy = computeModulation(entropyValue, w, False)
confEntropy = array(modulentropy - self.threshold) / self.threshold
confEntropy[confEntropy > 1] = 1
conf = self.new_result(data_mode='value', time_mode='framewise')
conf.id_metadata.id += '.' + 'confidence'
conf.id_metadata.name += ' ' + 'Confidence'
conf.data_object.value = confEntropy
self.process_pipe.results.add(conf)
# Binary Entropy
binaryEntropy = modulentropy > self.threshold
binaryEntropy = binary_opening(
binaryEntropy, [1] * (self.smoothLen * 2))
convert = {False: 0, True: 1}
label = {0: 'NonSpeech', 1: 'Speech'}
segList = segmentFromValues(binaryEntropy)
segs = self.new_result(data_mode='label', time_mode='segment')
segs.id_metadata.id += '.' + 'segments'
segs.id_metadata.name += ' ' + 'Segments'
segs.label_metadata.label = label
segs.data_object.label = [convert[s[2]] for s in segList]
segs.data_object.time = [(float(s[0]) * self.blocksize() /
self.samplerate())
for s in segList]
segs.data_object.duration = [(float(s[1] - s[0] + 1) * self.blocksize() /
self.samplerate())
for s in segList]
self.process_pipe.results.add(segs)
return
def post_process(self):
'''
'''
# Creation of the pass-band filter
Wo = self.frequency_center / self.samplerate()
Wn = [Wo - (self.frequency_width / 2) / self.samplerate(),
Wo + (self.frequency_width / 2) / self.samplerate()]
num = firwin(self.orderFilter, Wn, pass_zero=False)
# Energy on the frequency range
self.energy4hz = array(self.energy4hz)
energy = lfilter(num, 1, self.energy4hz.T, 0)
energy = sum(energy)
# Normalization
if self.normalizeEnergy and energy.any():
energy = energy / mean(energy)
# Energy Modulation
frameLenModulation = int(
self.modulLen * self.samplerate() / self.blocksize())
modEnergyValue = computeModulation(energy, frameLenModulation, True)
# Confidence Index
conf = array(modEnergyValue - self.threshold) / self.threshold
conf[conf > 1] = 1
modEnergy = self.new_result(data_mode='value', time_mode='framewise')
modEnergy.id_metadata.id += '.' + 'energy_confidence'
modEnergy.id_metadata.name += ' ' + 'Energy Confidence'
modEnergy.data_object.value = conf
self.process_pipe.results.add(modEnergy)
# Segment
convert = {False: 0, True: 1}
label = {0: 'nonSpeech', 1: 'Speech'}
segList = segmentFromValues(modEnergyValue > self.threshold)
# Hint : Median filtering could imrove smoothness of the result
# from scipy.signal import medfilt
# segList = segmentFromValues(medfilt(modEnergyValue > self.threshold, 31))
segs = self.new_result(data_mode='label', time_mode='segment')
segs.id_metadata.id += '.' + 'segments'
segs.id_metadata.name += ' ' + 'Segments'
segs.label_metadata.label = label
segs.data_object.label = [convert[s[2]] for s in segList]
segs.data_object.time = [(float(s[0]) * self.blocksize() /
self.samplerate())
for s in segList]
segs.data_object.duration = [(float(s[1]-s[0]+1) * self.blocksize() /
self.samplerate())
for s in segList]
self.process_pipe.results.add(segs)
return
