def get_patterns(self,E,phns,phn_times,s,
context=False,template_length=32):
"""
Parameters
----------
E: array
edgemap features
phns: array
strings representing the labels for the utterance
phn_times: array
times when the
"""
feature_start, \
feature_step, num_features =\
esp._get_feature_label_times(s,
self.num_window_samples,
self.num_window_step_samples)
feature_labels, \
feature_label_transitions \
= esp._get_labels(phn_times,
phns,
feature_start,
feature_step,
num_features,
self.sample_rate)
pattern_times = esp.get_pattern_times(self.patterns,
phns,
feature_label_transitions)
if context:
return [E[:,max(pattern_time[0]-template_length/3,0):\
min(pattern_time[0]+template_length+1+ (template_length)/3,E.shape[1])]\
for pattern_time in pattern_times]
else:
return [E[:,pattern_time[0]:pattern_time[1]+1]\
for pattern_time in pattern_times]
def get_patterns_specs(self,S,phns,phn_times,s,
offset=3):
first_window_s_avg, window_s_avg_step, num_windows = esp._get_spectrogram_label_times(s,
self.num_window_samples,
self.num_window_step_samples)
spec_labels, \
spec_label_transitions \
= esp._get_labels(phn_times,
phns,
first_window_s_avg,
window_s_avg_step,
num_windows,
self.sample_rate)
pattern_times = esp.get_pattern_times(self.patterns,
phns,
spec_label_transitions)
return [S[:,pattern_time[0]-offset:pattern_time[1]+1+offset]\
for pattern_time in pattern_times]
def get_pattern_times(self,phns,phn_times,s,
template_length=32):
feature_start, \
feature_step, num_features =\
esp._get_feature_label_times(s,
self.num_window_samples,
self.num_window_step_samples)
feature_labels, \
feature_label_transitions \
= esp._get_labels(phn_times,
phns,
feature_start,
feature_step,
num_features,
self.sample_rate)
pattern_times = esp.get_pattern_times(self.patterns,
phns,
feature_label_transitions)
return pattern_times
def get_pattern_fronts_backs(self,E,phns,phn_times,s,bg_len,
context=False,part_radius=5):
"""
Parameters
----------
E: array
edgemap features
phns: array
strings representing the labels for the utterance
phn_times: array
times when the
"""
feature_start, \
feature_step, num_features =\
esp._get_feature_label_times(s,
self.num_window_samples,
self.num_window_step_samples)
feature_labels, \
feature_label_transitions \
= esp._get_labels(phn_times,
phns,
feature_start,
feature_step,
num_features,
self.sample_rate)
pattern_times = esp.get_pattern_times(self.patterns,
phns,
feature_label_transitions)
if context:
return [(E[:,max(pattern_time[0]-part_radius,0):\
min(pattern_time[0]+part_radius,E.shape[0])],\
E[:,max(pattern_time[1]-part_radius,0):\
min(pattern_time[1]+part_radius,E.shape[0])],\
pattern_time) for pattern_time in pattern_times]
else:
return [(E[:,max(pattern_time[0]-part_radius,0):\
min(pattern_time[0]+part_radius,E.shape[1])],\
E[:,max(pattern_time[1]-part_radius,0):\
min(pattern_time[1]+part_radius,E.shape[1])],\
pattern_time,part_radius) for pattern_time in pattern_times]
def get_patterns_negative(self,E,phns,phn_times,s,length):
""" Returns a negative example for the given pattern
Parameters
----------
E: array
edgemap features
phns: array
strings representing the labels for the utterance
phn_times: array
times when the
"""
feature_start, \
feature_step, num_features =\
esp._get_feature_label_times(s,
self.num_window_samples,
self.num_window_step_samples)
feature_labels, \
feature_label_transitions \
= esp._get_labels(phn_times,
phns,
feature_start,
feature_step,
num_features,
self.sample_rate)
pattern_times = esp.get_pattern_times(self.patterns,
phns,
feature_label_transitions)
end_time = E.shape[1]-length-3
start_time = length+3
neg_pattern_time = np.random.randint(start_time,end_time)
# make sure that its not close to the start time of a patter
while self._within_pattern_tolerance(neg_pattern_time,
pattern_times,
length):
neg_pattern_time = np.random.randint(start_time,end_time)
return E[:,neg_pattern_time:neg_pattern_time+length].copy(), E[:,max(neg_pattern_time-length,0):neg_pattern_time].copy()
