def test_real_metrics():
_, source = example_file_data_sources_for_acoustic_model()
X = FileSourceDataset(source)
lengths = [len(x) for x in X]
X = X.asarray()
mgc = X[:, :, :source.mgc_dim // 3]
lf0 = X[:, :, source.lf0_start_idx]
vuv = (X[:, :, source.vuv_start_idx] > 0).astype(np.int)
bap = X[:, :, source.bap_start_idx]
mgc_tgt = mgc + 0.01
lf0_tgt = lf0 + 0.01
vuv_tgt = vuv.copy()
bap_tgt = bap + 0.01
mcd = metrics.melcd(mgc, mgc_tgt, lengths)
bap_mcd = metrics.melcd(bap, bap_tgt, lengths)
lf0_mse = metrics.lf0_mean_squared_error(lf0, vuv, lf0_tgt, vuv_tgt,
lengths)
vuv_err = metrics.vuv_error(vuv, vuv_tgt)
assert mcd > 0
assert bap_mcd > 0
assert lf0_mse > 0
assert vuv_err == 0.0
def test_dtw_frame_length_adjastment():
_, X = example_file_data_sources_for_duration_model()
X = FileSourceDataset(X)
X_unaligned = X.asarray()
# This should trigger frame length adjastment
Y_unaligned = np.pad(X_unaligned, [(0, 0), (5, 0), (0, 0)],
mode="constant", constant_values=0)
Y_unaligned = Y_unaligned[:, :-5, :]
for aligner in [DTWAligner(), IterativeDTWAligner(
n_iter=1, max_iter_gmm=1, n_components_gmm=1)]:
X_aligned, Y_aligned = aligner.transform((X_unaligned, Y_unaligned))
assert X_aligned.shape == Y_aligned.shape
if overwrite:
skip_feature_extraction = False
if skip_feature_extraction:
print("Features seems to be prepared, skipping feature extraction.")
sys.exit(0)
# Create dirs
for speaker, name in [(source_speaker, "X"), (target_speaker, "Y")]:
d = join(dst_dir, name)
print("Destination dir for {}: {}".format(speaker, d))
if not exists(d):
os.makedirs(d)
# Convert to arrays
print("Convert datasets to arrays")
X, Y = X_dataset.asarray(verbose=1), Y_dataset.asarray(verbose=1)
# Alignment
print("Perform alignment")
X, Y = DTWAligner().transform((X, Y))
print("Save features to disk")
for idx, (x, y) in tqdm(enumerate(zip(X, Y))):
# paths
src_name = splitext(basename(X_dataset.collected_files[idx][0]))[0]
tgt_name = splitext(basename(Y_dataset.collected_files[idx][0]))[0]
src_path = join(dst_dir, "X", src_name)
tgt_path = join(dst_dir, "Y", tgt_name)
# Trim and ajast frames
x = P.trim_zeros_frames(x)
if overwrite:
skip_feature_extraction = False
if skip_feature_extraction:
print("Features seems to be prepared, skipping feature extraction.")
sys.exit(0)
# Create dirs
for speaker, name in [(source_speaker, "X"), (target_speaker, "Y")]:
d = join(dst_dir, name)
print("Destination dir for {}: {}".format(speaker, d))
if not exists(d):
os.makedirs(d)
# Convert to arrays
print("Convert datasets to arrays")
X, Y = X_dataset.asarray(verbose=1), Y_dataset.asarray(verbose=1)
# Alignment
print("Perform alignment")
X, Y = DTWAligner().transform((X, Y))
print("Save features to disk")
for idx, (x, y) in tqdm(enumerate(zip(X, Y))):
# paths
src_name = splitext(basename(X_dataset.collected_files[idx][0]))[0]
tgt_name = splitext(basename(Y_dataset.collected_files[idx][0]))[0]
src_path = join(dst_dir, "X", src_name)
tgt_path = join(dst_dir, "Y", tgt_name)
# Trim and ajast frames
x = P.trim_zeros_frames(x)