def get_plp_dd(wav_fn, norm):
"""Return the MFCCs with deltas and delta-deltas for a audio file."""
audio = Audio.load(wav_fn)
processor = PlpProcessor(sample_rate=audio.sample_rate, window_type="hamming",frame_length=0.025, frame_shift=0.01,
low_freq=0, vtln_low=60, vtln_high=7200, high_freq=audio.sample_rate/2)
plp_static = processor.process(audio, vtln_warp=1.0)
d_processor = DeltaPostProcessor(order=2)
plp_deltas = d_processor.process(plp_static)
features = np.float64(plp_deltas._to_dict()["data"])
if norm == "cmvn":
features = (features - np.mean(features, axis=0)) / np.std(features, axis=0)
return features
def get_mfcc_vtln(wav_fn, f, norm, lang):
"""Return the MFCCs with deltas and delta-deltas for a audio file."""
ref = os.path.basename(f).replace(".wav", "")
if not os.path.isfile("warps_{}.pkl".format(lang)):
if os.path.isfile('warps_{}.txt'.format(lang)):
factors = {}
with open('warps_{}.txt'.format(lang), mode='r',
encoding='utf-8') as opfile:
wop = opfile.read().split('\n')
for line in wop:
if len(line) > 1:
l_sp = line.split()
factors[l_sp[0]] = float(l_sp[1])
print(factors)
with open('warps_{}.pkl'.format(lang), mode='wb') as opfile:
pickle.dump(factors, opfile)
else:
print('no warp factors found')
exit()
with open("warps_{}.pkl".format(lang), mode="rb") as op:
factors = pickle.load(op)
warp = float(factors[ref])
audio = Audio.load(wav_fn)
processor = MfccProcessor(sample_rate=audio.sample_rate,
window_type="hamming",
frame_length=0.025,
frame_shift=0.01,
cepstral_lifter=26.0,
low_freq=0,
vtln_low=60,
vtln_high=7200,
high_freq=audio.sample_rate / 2)
d_processor = DeltaPostProcessor(order=2)
mfcc_static = processor.process(audio, vtln_warp=warp)
mfcc_deltas = d_processor.process(mfcc_static)
features = np.float64(mfcc_deltas._to_dict()["data"])
if norm == "cmvn":
features = (features - np.mean(features, axis=0)) / np.std(features,
axis=0)
return features
def get_features(self, y, sample_rate):
"""Feature extraction
Parameters
----------
y : (n_samples, 1) numpy array
Waveform
sample_rate : int
Sample rate
Returns
-------
data : (n_frames, n_dimensions) numpy array
Features
"""
# scale the audio signal between -1 and 1 before
# creating audio object w/ shennong: Do this because
# when pyannote uses "data augmentation", it normalizes
# the signal, but when loading the data without data
# augmentation it doesn't normalize it.
y = y / np.max((-np.min(y), np.max(y)))
# create audio object for shennong
audio = Audio(data=y, sample_rate=sample_rate)
# MFCC parameters
processor = MfccProcessor(sample_rate=sample_rate)
processor.dither = self.dither
processor.preemph_coeff = self.preemph_coeff
processor.remove_dc_offset = self.remove_dc_offset
processor.window_type = self.window_type
processor.blackman_coeff = self.blackman_coeff
processor.vtln_low = self.vtln_low
processor.vtln_high = self.vtln_high
processor.energy_floor = self.energy_floor
processor.raw_energy = self.raw_energy
processor.cepstral_lifter = self.cepstral_lifter
processor.htk_compat = self.htk_compat
processor.low_freq = self.mfccLowFreq
processor.high_freq = self.mfccHighFreq # defines it as (nyquist - 100)
processor.use_energy = self.e
processor.num_ceps = self.coefs
processor.snip_edges = False # end with correct number of frames
# MFCC extraction
#audio = Audio(data=y, sample_rate=sample_rate)
mfcc = processor.process(audio)
# compute deltas
if self.D:
# define first or second order derivative
if not self.DD:
derivative_proc = DeltaPostProcessor(order=1)
else:
derivative_proc = DeltaPostProcessor(order=2)
# process Mfccs
mfcc = derivative_proc.process(mfcc)
# Compute CMVN
if self.with_cmvn:
# define cmvn
postproc = CmvnPostProcessor(self.get_dimension(), stats=None)
# accumulate stats
stats = postproc.accumulate(mfcc)
# process cmvn
mfcc = postproc.process(mfcc)
# Compute Pitch
if self.with_pitch:
# extract pitch
pitch = self.get_pitch(audio, self.pitchFmin, self.pitchFmax)
mfcc = self.concatenate_with_pitch(mfcc.data, pitch.data)
else:
mfcc = mfcc.data
return mfcc