def compute_distortions(y_static,
y_hat_static,
Y_data_mean,
Y_data_std,
lengths=None):
if hp.name == "acoustic":
mgc, lf0, vuv, bap = split_streams(y_static, Y_data_mean, Y_data_std)
mgc_hat, lf0_hat, vuv_hat, bap_hat = split_streams(
y_hat_static, Y_data_mean, Y_data_std)
try:
f0_mse = metrics.lf0_mean_squared_error(lf0,
vuv,
lf0_hat,
vuv_hat,
lengths=lengths,
linear_domain=True)
except ZeroDivisionError:
f0_mse = np.nan
distortions = {
"mcd": metrics.melcd(mgc[:, :, 1:],
mgc_hat[:, :, 1:],
lengths=lengths),
"bap_mcd": metrics.melcd(bap, bap_hat, lengths=lengths) / 10.0,
"f0_rmse": np.sqrt(f0_mse),
"vuv_err": metrics.vuv_error(vuv, vuv_hat, lengths=lengths),
}
elif hp.name == "duration":
y_static_invscale = P.inv_scale(y_static, Y_data_mean, Y_data_std)
y_hat_static_invscale = P.inv_scale(y_hat_static, Y_data_mean,
Y_data_std)
distortions = {
"dur_rmse":
math.sqrt(
metrics.mean_squared_error(y_static_invscale,
y_hat_static_invscale,
lengths=lengths))
}
elif hp.name == "vc":
static_dim = hp.order
y_static_invscale = P.inv_scale(y_static, Y_data_mean[:static_dim],
Y_data_std[:static_dim])
y_hat_static_invscale = P.inv_scale(y_hat_static,
Y_data_mean[:static_dim],
Y_data_std[:static_dim])
distortions = {
"mcd":
metrics.melcd(y_static_invscale,
y_hat_static_invscale,
lengths=lengths)
}
else:
assert False
return distortions
def compute_distortions(pred_out_feats, out_feats, lengths, out_scaler):
assert pred_out_feats.shape == out_feats.shape
out_feats = out_scaler.inverse_transform(out_feats)
pred_out_feats = out_scaler.inverse_transform(pred_out_feats)
dist = {}
try:
dist["ObjEval_RMSE"] = np.sqrt(
metrics.mean_squared_error(out_feats,
pred_out_feats,
lengths=lengths))
except ZeroDivisionError:
pass
return dist