def test_trim_remove_zeros_frames():
fs, x = wavfile.read(example_audio_file())
frame_period = 5
x = x.astype(np.float64)
f0, timeaxis = pyworld.dio(x, fs, frame_period=frame_period)
spectrogram = pyworld.cheaptrick(x, f0, timeaxis, fs)
aperiodicity = pyworld.d4c(x, f0, timeaxis, fs)
for mat in [spectrogram, aperiodicity]:
trimmed = trim_zeros_frames(mat)
assert trimmed.shape[1] == mat.shape[1]
for mat in [spectrogram, aperiodicity]:
trimmed = remove_zeros_frames(mat)
assert trimmed.shape[1] == mat.shape[1]
def make_dataset_to_array(dataset, keys=None):
if keys is None:
keys = sorted(dataset.keys())
data = None
for key in keys:
d = dataset[key]
if isinstance(d, tuple):
d = np.hstack(d)
d = remove_zeros_frames(d)
if data is None:
data = copy.copy(d)
else:
len_data = len(data)
data.resize(len_data + len(d), d.shape[-1])
data[len_data:, :] = d
return data
# Drop 1st (power) dimension
X_aligned, Y_aligned = X_aligned[:, :, 1:], Y_aligned[:, :, 1:]
# Append delta features
static_dim = X_aligned.shape[-1]
if use_delta:
X_aligned = apply_each2d_trim(delta_features, X_aligned, windows)
Y_aligned = apply_each2d_trim(delta_features, Y_aligned, windows)
# plot_parallel(X_aligned[idx],Y_aligned[idx])
# Finally, we get joint feature matrix
XY = np.concatenate((X_aligned, Y_aligned), axis=-1).reshape(-1, X_aligned.shape[-1] * 2)
print(XY.shape)
XY = remove_zeros_frames(XY)
print(XY.shape)
# Model
gmm = GaussianMixture(
n_components=64, covariance_type="full", max_iter=100, verbose=1)
gmm.fit(XY)
# Visualize model
# Means
# for k in range(3):
# plot(gmm.means_[k], linewidth=1.5, label="Mean of mixture {}".format(k+1))
# legend(prop={"size": 16})
def make_expected_dataset(data_root, use_delta):
from pathlib import Path
from nnmnkwii.datasets import PaddedFileSourceDataset
from nnmnkwii.datasets.cmu_arctic import CMUArcticWavFileDataSource
from nnmnkwii.metrics import melcd
from nnmnkwii.preprocessing import (delta_features, remove_zeros_frames,
trim_zeros_frames)
from nnmnkwii.preprocessing.alignment import DTWAligner
from nnmnkwii.util import apply_each2d_trim
max_files = 100 # number of utterances to be used.
test_size = 0.03
windows = DELTA_WINDOWS
class MyFileDataSource(CMUArcticWavFileDataSource):
def __init__(self, *args, **kwargs):
super(MyFileDataSource, self).__init__(*args, **kwargs)
self.test_paths = None
def collect_files(self):
paths = [
Path(path)
for path in super(MyFileDataSource, self).collect_files()
]
paths_train, paths_test = train_test_split(paths,
test_size=test_size,
random_state=1234)
# keep paths for later testing
self.test_paths = paths_test
return paths_train
def collect_features(self, path):
feature = kwiiyatta.analyze_wav(path)
s = trim_zeros_frames(feature.spectrum_envelope)
return feature.mel_cepstrum.data[:len(s)] # トリムするフレームが手前にずれてるのでは？
clb_source = MyFileDataSource(data_root=data_root,
speakers=["clb"],
max_files=max_files)
slt_source = MyFileDataSource(data_root=data_root,
speakers=["slt"],
max_files=max_files)
X = PaddedFileSourceDataset(clb_source, 1200).asarray()
Y = PaddedFileSourceDataset(slt_source, 1200).asarray()
# Alignment
X_aligned, Y_aligned = DTWAligner(verbose=0, dist=melcd).transform((X, Y))
# Drop 1st (power) dimension
X_aligned, Y_aligned = X_aligned[:, :, 1:], Y_aligned[:, :, 1:]
if use_delta:
X_aligned = apply_each2d_trim(delta_features, X_aligned, windows)
Y_aligned = apply_each2d_trim(delta_features, Y_aligned, windows)
XY = (np.concatenate((X_aligned, Y_aligned),
axis=-1).reshape(-1, X_aligned.shape[-1] * 2))
return remove_zeros_frames(XY)
