def main(*argv):
argv = argv if argv else sys.argv[1:]
# Options for python
description = 'estimate joint feature of source and target speakers'
parser = argparse.ArgumentParser(description=description)
parser.add_argument('speaker', type=str, help='Input speaker label')
parser.add_argument('list_file',
type=str,
help='List file of the input speaker')
parser.add_argument('pair_dir',
type=str,
help='Statistics directory of the speaker')
args = parser.parse_args(argv)
# open h5 files
h5_dir = os.path.join(args.pair_dir, 'h5')
statspath = os.path.join(args.pair_dir, 'stats', args.speaker + '.h5')
h5 = HDF5(statspath, mode='a')
# estimate and save F0 statistics
f0stats = F0statistics()
f0s = read_feats(args.list_file, h5_dir, ext='f0')
f0stats = f0stats.estimate(f0s)
h5.save(f0stats, ext='f0stats')
print("f0stats save into " + statspath)
# estimate and save GV of orginal and target speakers
gv = GV()
mceps = read_feats(args.list_file, h5_dir, ext='mcep')
gvstats = gv.estimate(mceps)
h5.save(gvstats, ext='gv')
print("gvstats save into " + statspath)
h5.close()
def main(*argv):
argv = argv if argv else sys.argv[1:]
# Options for python
dcp = 'Extract aoucstic features for the speaker'
parser = argparse.ArgumentParser(description=dcp)
parser.add_argument('--f0rate',
type=float,
default=-1,
help='Original speaker label')
parser.add_argument('speaker', type=str, help='Original speaker label')
parser.add_argument('org_yml',
type=str,
help='Yml file of the original speaker')
parser.add_argument('tar_yml',
type=str,
help='Yml file of the target speaker')
parser.add_argument('org_train_list',
type=str,
help='List file of the original speaker')
parser.add_argument('org_eval_list',
type=str,
help='List file of the original speaker')
parser.add_argument('tar_train_list',
type=str,
help='List file of the target speaker')
parser.add_argument('wav_dir',
type=str,
help='Wav file directory of the speaker')
args = parser.parse_args(argv)
# read parameters from speaker yml
org_conf = SpeakerYML(args.org_yml)
tar_conf = SpeakerYML(args.tar_yml)
if args.f0rate == -1:
# get f0 list to calculate F0 transformation ratio
org_f0s = get_f0s_from_list(org_conf, args.org_train_list,
args.wav_dir)
tar_f0s = get_f0s_from_list(tar_conf, args.tar_train_list,
args.wav_dir)
# calculate F0 statistics of original and target speaker
f0stats = F0statistics()
orgf0stats = f0stats.estimate(org_f0s)
tarf0stats = f0stats.estimate(tar_f0s)
# calculate F0 transformation ratio between original and target speakers
f0rate = np.round(np.exp(tarf0stats[0] - orgf0stats[0]), decimals=2)
else:
f0rate = args.f0rate
print('F0 transformation ratio: ' + str(f0rate))
# F0 transformation of original waveform in both train and eval list files
transform_f0_from_list(args.speaker, f0rate, org_conf.wav_fs,
args.org_train_list, args.wav_dir)
transform_f0_from_list(args.speaker, f0rate, org_conf.wav_fs,
args.org_eval_list, args.wav_dir)
def test_estimate_F0statistics(self):
f0stats = F0statistics()
orgf0s = []
for i in range(1, 4):
orgf0s.append(200 * np.r_[np.random.rand(100 * i), np.zeros(100)])
orgf0stats = f0stats.estimate(orgf0s)
tarf0s = []
for i in range(1, 8):
tarf0s.append(300 * np.r_[np.random.rand(100 * i), np.zeros(100)])
tarf0stats = f0stats.estimate(tarf0s)
orgf0 = 200 * np.r_[np.random.rand(100 * i), np.zeros(100)]
cvf0 = f0stats.convert(orgf0, orgf0stats, tarf0stats)
assert len(orgf0) == len(cvf0)
def main(*argv):
argv = argv if argv else sys.argv[1:]
# Options for python
description = 'estimate joint feature of source and target speakers'
parser = argparse.ArgumentParser(description=description)
parser.add_argument('-gmmmode',
'--gmmmode',
type=str,
default=None,
help='mode of the GMM [None, diff, or intra]')
parser.add_argument('org', type=str, help='Original speaker')
parser.add_argument('tar', type=str, help='Target speaker')
parser.add_argument('org_yml',
type=str,
help='Yml file of the original speaker')
parser.add_argument('pair_yml',
type=str,
help='Yml file of the speaker pair')
parser.add_argument('eval_list_file',
type=str,
help='List file for evaluation')
parser.add_argument('wav_dir',
type=str,
help='Directory path of source spekaer')
parser.add_argument('pair_dir',
type=str,
help='Directory path of pair directory')
args = parser.parse_args(argv)
# read parameters from speaker yml
sconf = SpeakerYML(args.org_yml)
pconf = PairYML(args.pair_yml)
# read GMM for mcep
mcepgmmpath = os.path.join(args.pair_dir, 'model/GMM_mcep.pkl')
mcepgmm = GMMConvertor(
n_mix=pconf.GMM_mcep_n_mix,
covtype=pconf.GMM_mcep_covtype,
gmmmode=args.gmmmode,
)
param = joblib.load(mcepgmmpath)
mcepgmm.open_from_param(param)
print("GMM for mcep conversion mode: {}".format(args.gmmmode))
# read F0 statistics
stats_dir = os.path.join(args.pair_dir, 'stats')
orgstatspath = os.path.join(stats_dir, args.org + '.h5')
orgstats_h5 = HDF5(orgstatspath, mode='r')
orgf0stats = orgstats_h5.read(ext='f0stats')
orgstats_h5.close()
# read F0 and GV statistics for target
tarstatspath = os.path.join(stats_dir, args.tar + '.h5')
tarstats_h5 = HDF5(tarstatspath, mode='r')
tarf0stats = tarstats_h5.read(ext='f0stats')
targvstats = tarstats_h5.read(ext='gv')
tarstats_h5.close()
# read GV statistics for converted mcep
cvgvstatspath = os.path.join(args.pair_dir, 'model', 'cvgv.h5')
cvgvstats_h5 = HDF5(cvgvstatspath, mode='r')
cvgvstats = cvgvstats_h5.read(ext='cvgv')
diffcvgvstats = cvgvstats_h5.read(ext='diffcvgv')
cvgvstats_h5.close()
mcepgv = GV()
f0stats = F0statistics()
# constract FeatureExtractor class
feat = FeatureExtractor(analyzer=sconf.analyzer,
fs=sconf.wav_fs,
fftl=sconf.wav_fftl,
shiftms=sconf.wav_shiftms,
minf0=sconf.f0_minf0,
maxf0=sconf.f0_maxf0)
# constract Synthesizer class
synthesizer = Synthesizer(fs=sconf.wav_fs,
fftl=sconf.wav_fftl,
shiftms=sconf.wav_shiftms)
# test directory
test_dir = os.path.join(args.pair_dir, 'test')
os.makedirs(os.path.join(test_dir, args.org), exist_ok=True)
# conversion in each evaluation file
with open(args.eval_list_file, 'r') as fp:
for line in fp:
# open wav file
f = line.rstrip()
wavf = os.path.join(args.wav_dir, f + '.wav')
fs, x = wavfile.read(wavf)
x = x.astype(np.float)
x = low_cut_filter(x, fs, cutoff=70)
assert fs == sconf.wav_fs
# analyze F0, mcep, and ap
f0, spc, ap = feat.analyze(x)
mcep = feat.mcep(dim=sconf.mcep_dim, alpha=sconf.mcep_alpha)
mcep_0th = mcep[:, 0]
# convert F0
cvf0 = f0stats.convert(f0, orgf0stats, tarf0stats)
# convert mcep
cvmcep_wopow = mcepgmm.convert(static_delta(mcep[:, 1:]),
cvtype=pconf.GMM_mcep_cvtype)
cvmcep = np.c_[mcep_0th, cvmcep_wopow]
# synthesis VC w/ GV
if args.gmmmode is None:
cvmcep_wGV = mcepgv.postfilter(cvmcep,
targvstats,
cvgvstats=cvgvstats,
alpha=pconf.GV_morph_coeff,
startdim=1)
wav = synthesizer.synthesis(
cvf0,
cvmcep_wGV,
ap,
rmcep=mcep,
alpha=sconf.mcep_alpha,
)
wavpath = os.path.join(test_dir, f + '_VC.wav')
# synthesis DIFFVC w/ GV
if args.gmmmode == 'diff':
cvmcep[:, 0] = 0.0
cvmcep_wGV = mcepgv.postfilter(mcep + cvmcep,
targvstats,
cvgvstats=diffcvgvstats,
alpha=pconf.GV_morph_coeff,
startdim=1) - mcep
wav = synthesizer.synthesis_diff(
x,
cvmcep_wGV,
rmcep=mcep,
alpha=sconf.mcep_alpha,
)
wavpath = os.path.join(test_dir, f + '_DIFFVC.wav')
# write waveform
if not os.path.exists(os.path.join(test_dir, f)):
os.makedirs(os.path.join(test_dir, f))
wav = np.clip(wav, -32768, 32767)
wavfile.write(wavpath, fs, wav.astype(np.int16))
print(wavpath)