def melspecgrams_to_specgrams(self, melspecgrams):
"""Converts melspecgrams to specgrams.
Args:
melspecgrams: Tensor of log magnitudes and instantaneous frequencies,
shape [batch, time, freq, 2], mel scaling of frequencies.
Returns:
specgrams: Tensor of log magnitudes and instantaneous frequencies,
shape [batch, time, freq, 2].
"""
if self._mel_downscale is None:
return melspecgrams
logmelmag2 = melspecgrams[:, :, :, 0]
mel_p = melspecgrams[:, :, :, 1]
mel2l = tf.to_float(self._mel_to_linear_matrix())
mag2 = tf.tensordot(tf.exp(logmelmag2), mel2l, 1)
logmag = 0.5 * self._safe_log(mag2)
mel_phase_angle = tf.cumsum(mel_p * np.pi, axis=-2)
phase_angle = tf.tensordot(mel_phase_angle, mel2l, 1)
p = spectral_ops.instantaneous_frequency(phase_angle)
return tf.concat([logmag[:, :, :, tf.newaxis], p[:, :, :, tf.newaxis]],
axis=-1)
def melspecgrams_to_specgrams(self, melspecgrams):
"""Converts melspecgrams to specgrams.
Args:
melspecgrams: Tensor of log magnitudes and instantaneous frequencies,
shape [batch, time, freq, 2], mel scaling of frequencies.
Returns:
specgrams: Tensor of log magnitudes and instantaneous frequencies,
shape [batch, time, freq, 2].
"""
if self._mel_downscale is None:
return melspecgrams
logmelmag2 = melspecgrams[:, :, :, 0]
mel_p = melspecgrams[:, :, :, 1]
mel2l = tf.to_float(self._mel_to_linear_matrix())
mag2 = tf.tensordot(tf.exp(logmelmag2), mel2l, 1)
logmag = 0.5 * self._safe_log(mag2)
mel_phase_angle = tf.cumsum(mel_p * np.pi, axis=-2)
phase_angle = tf.tensordot(mel_phase_angle, mel2l, 1)
p = spectral_ops.instantaneous_frequency(phase_angle)
return tf.concat(
[logmag[:, :, :, tf.newaxis], p[:, :, :, tf.newaxis]], axis=-1)
def specgrams_to_melspecgrams(self, specgrams):
"""Converts specgrams to melspecgrams.
Args:
specgrams: Tensor of log magnitudes and instantaneous frequencies,
shape [batch, time, freq, 2].
Returns:
melspecgrams: Tensor of log magnitudes and instantaneous frequencies,
shape [batch, time, freq, 2], mel scaling of frequencies.
"""
if self._mel_downscale is None:
return specgrams
logmag = specgrams[:, :, :, 0]
p = specgrams[:, :, :, 1]
mag2 = tf.exp(2.0 * logmag)
phase_angle = tf.cumsum(p * np.pi, axis=-2)
l2mel = tf.to_float(self._linear_to_mel_matrix())
logmelmag2 = self._safe_log(tf.tensordot(mag2, l2mel, 1))
mel_phase_angle = tf.tensordot(phase_angle, l2mel, 1)
mel_p = spectral_ops.instantaneous_frequency(mel_phase_angle)
return tf.concat(
[logmelmag2[:, :, :, tf.newaxis], mel_p[:, :, :, tf.newaxis]],
axis=-1)
def specgrams_to_melspecgrams(self, specgrams):
"""Converts specgrams to melspecgrams.
Args:
specgrams: Tensor of log magnitudes and instantaneous frequencies,
shape [batch, time, freq, 2].
Returns:
melspecgrams: Tensor of log magnitudes and instantaneous frequencies,
shape [batch, time, freq, 2], mel scaling of frequencies.
"""
if self._mel_downscale is None:
return specgrams
logmag = specgrams[:, :, :, 0]
p = specgrams[:, :, :, 1]
mag2 = tf.exp(2.0 * logmag)
phase_angle = tf.cumsum(p * np.pi, axis=-2)
l2mel = tf.to_float(self._linear_to_mel_matrix())
logmelmag2 = self._safe_log(tf.tensordot(mag2, l2mel, 1))
mel_phase_angle = tf.tensordot(phase_angle, l2mel, 1)
mel_p = spectral_ops.instantaneous_frequency(mel_phase_angle)
return tf.concat(
[logmelmag2[:, :, :, tf.newaxis], mel_p[:, :, :, tf.newaxis]], axis=-1)
def testInstantaneousFrequency(self, shape, axis):
# Instantaneous Frequency in numpy
phase_np = np.pi * (2 * np.random.rand(*shape) - 1)
unwrapped_np = np.unwrap(phase_np, axis=axis)
dphase_np = np.diff(unwrapped_np, axis=axis)
# Append with initial phase
s = [slice(None),] * unwrapped_np.ndim
s[axis] = slice(0, 1)
slice_np = unwrapped_np[s]
dphase_np = np.concatenate([slice_np, dphase_np], axis=axis) / np.pi
phase_tf = tf.convert_to_tensor(phase_np)
with self.cached_session() as sess:
dphase_tf = sess.run(spectral_ops.instantaneous_frequency(phase_tf,
time_axis=axis))
self.assertAllClose(dphase_np, dphase_tf)
def testInstantaneousFrequency(self, shape, axis):
# Instantaneous Frequency in numpy
phase_np = np.pi * (2 * np.random.rand(*shape) - 1)
unwrapped_np = np.unwrap(phase_np, axis=axis)
dphase_np = np.diff(unwrapped_np, axis=axis)
# Append with initial phase
s = [slice(None),] * unwrapped_np.ndim
s[axis] = slice(0, 1)
slice_np = unwrapped_np[s]
dphase_np = np.concatenate([slice_np, dphase_np], axis=axis) / np.pi
phase_tf = tf.convert_to_tensor(phase_np)
with self.cached_session() as sess:
dphase_tf = sess.run(spectral_ops.instantaneous_frequency(phase_tf,
time_axis=axis))
self.assertAllClose(dphase_np, dphase_tf)
def stfts_to_specgrams(self, stfts):
"""Converts stfts to specgrams.
Args:
stfts: Complex64 tensor of stft, shape [batch, time, freq, 1].
Returns:
specgrams: Tensor of log magnitudes and instantaneous frequencies,
shape [batch, time, freq, 2].
"""
stfts = stfts[:, :, :, 0]
logmag = self._safe_log(tf.abs(stfts))
phase_angle = tf.angle(stfts)
if self._ifreq:
p = spectral_ops.instantaneous_frequency(phase_angle)
else:
p = phase_angle / np.pi
return tf.concat([logmag[:, :, :, tf.newaxis], p[:, :, :, tf.newaxis]],
axis=-1)
def stfts_to_specgrams(self, stfts):
"""Converts stfts to specgrams.
Args:
stfts: Complex64 tensor of stft, shape [batch, time, freq, 1].
Returns:
specgrams: Tensor of log magnitudes and instantaneous frequencies,
shape [batch, time, freq, 2].
"""
stfts = stfts[:, :, :, 0]
logmag = self._safe_log(tf.abs(stfts))
phase_angle = tf.angle(stfts)
if self._ifreq:
p = spectral_ops.instantaneous_frequency(phase_angle)
else:
p = phase_angle / np.pi
return tf.concat(
[logmag[:, :, :, tf.newaxis], p[:, :, :, tf.newaxis]], axis=-1)
