espnet.nets.pytorch_backend.frontends.feature_transform.LogMel

source

class espnet.nets.pytorch_backend.frontends.feature_transform.LogMel(fs: int = 16000, n_fft: int = 512, n_mels: int = 80, fmin: float = 0.0, fmax: float | None = None, htk: bool = False, norm=1)

Bases: Module

Convert STFT to fbank feats.

The arguments is same as librosa.filters.mel

• Parameters:
  • fs – number > 0 [scalar] sampling rate of the incoming signal
  • n_fft – int > 0 [scalar] number of FFT components
  • n_mels – int > 0 [scalar] number of Mel bands to generate
  • fmin – float >= 0 [scalar] lowest frequency (in Hz)
  • fmax – float >= 0 [scalar] highest frequency (in Hz). If None, use fmax = fs / 2.0
  • htk – use HTK formula instead of Slaney
  • norm – {None, 1, np.inf} [scalar] if 1, divide the triangular mel weights by the width of the mel band (area normalization). Otherwise, leave all the triangles aiming for a peak value of 1.0

Initialize LogMel.

extra_repr()

Append an extra string representation.

forward(feat: Tensor, ilens: LongTensor) → Tuple[Tensor, LongTensor]

Calculate Logmel forward propagation.