nnmnkwii.autograd.mlpg

nnmnkwii.autograd.mlpg(mean_frames, variance_frames, windows)

Maximum Liklihood Paramter Generation (MLPG).

The parameters are almost same as nnmnkwii.functions.mlpg() expects. The differences are:

• The function assumes mean_frames as torch.autograd.Variable instead of numpy.ndarray.
• The fucntion assumes variances_frames as torch.FloatTensor instead of numpy.ndarray.

Parameters:

• mean_frames (torch.autograd.Variable) – Means
• variance_frames (torch.FloatTensor) – Variances
• windows (list) – A sequence of window specification

See also

nnmnkwii.functions.mlpg()