def comp_feat(self, sig, rate):
'''
compute the features
Args:
sig: the audio signal as a 1-D numpy array
rate: the sampling rate
Returns:
the features as a [seq_length x feature_dim] numpy array
'''
#snip the edges
sig = snip(sig, rate, float(self.conf['winlen']),
float(self.conf['winstep']))
feat, energy = base.mfcc(sig, rate, self.conf)
if self.conf['include_energy'] == 'True':
feat = np.append(feat, energy[:, np.newaxis], 1)
if self.conf['dynamic'] == 'delta':
feat = base.delta(feat)
elif self.conf['dynamic'] == 'ddelta':
feat = base.ddelta(feat)
elif self.conf['dynamic'] != 'nodelta':
raise Exception('unknown dynamic type')
return feat
def comp_feat(self, sig, rate):
"""
compute the features
Args:
sig: the audio signal as a 1-D numpy array
rate: the sampling rate
Returns:
the features as a [seq_length x feature_dim] numpy array
"""
# snip the edges
sig = snip(sig, rate, float(self.conf['winlen']),
float(self.conf['winstep']))
if 'scipy' in self.conf and self.conf['scipy'] == 'True':
feat = base.angspec_scipy(sig, rate, self.conf)
else:
feat = base.angspec(sig, rate, self.conf)
if self.conf['include_energy'] == 'True':
if 'scipy' in self.conf and self.conf['scipy'] == 'True':
_, energy = base.fbank_scipy(sig, rate, self.conf)
else:
_, energy = base.fbank(sig, rate, self.conf)
feat = np.append(feat, energy[:, np.newaxis], 1)
return feat
def __call__(self, sig, rate):
'''
compute the features
Args:
sig: the audio signal as a 1-D numpy array
rate: the sampling rate
Returns:
the features as a [seq_length x feature_dim] numpy array
'''
#snip the edges
sig = sigproc.snip(sig, rate, float(self.conf['winlen']),
float(self.conf['winstep']))
#compute the features
feats = self.comp_feat(sig, rate)
#apply vad
if self.conf['vad'] == 'True':
speechframes = vad(sig, rate, float(self.conf['winlen']),
float(self.conf['winstep']))
feats = feats[speechframes, :]
return feats
def comp_feat(self, sig, rate):
'''
compute the features
Args:
sig: the audio signal as a 1-D numpy array
rate: the sampling rate
Returns:
the features as a [seq_length x feature_dim] numpy array
'''
#snip the edges
sig = snip(sig, rate, float(self.conf['winlen']),
float(self.conf['winstep']))
feat = base.raw(sig)
return feat
def comp_feat(self, sig, rate):
"""
compute the features
Args:
sig: the audio signal as a 1-D numpy array
rate: the sampling rate
Returns:
the features as a [seq_length x feature_dim] numpy array
"""
# snip the edges
sig = snip(sig, rate, float(self.conf['winlen']),
float(self.conf['winstep']))
if 'scipy' in self.conf and self.conf['scipy'] == 'True':
feat = base.frames_scipy(sig, rate, self.conf)
else:
feat = base.frames(sig, rate, self.conf)
return feat
