espnet.nets.pytorch_backend.frontends.feature_transform.utterance_mvn

source

espnet.nets.pytorch_backend.frontends.feature_transform.utterance_mvn(x: Tensor, ilens: LongTensor, norm_means: bool = True, norm_vars: bool = False, eps: float = 1e-20) → Tuple[Tensor, LongTensor]

Apply utterance mean and variance normalization

• Parameters:
  • x – (B, T, D), assumed zero padded
  • ilens – (B, T, D)
  • norm_means
  • norm_vars
  • eps