torchaudio.functional.preemphasis

torchaudio.functional.preemphasis(waveform, coeff: float = 0.97) → Tensor

Pre-emphasizes a waveform along its last dimension, i.e. for each signal $x$ in waveform, computes output $y$ as

$$y[i] = x[i] - \text{coeff} \cdot x[i - 1]$$

Parameters:

• waveform (torch.Tensor) – Waveform, with shape (…, N).

• coeff (float, optional) – Pre-emphasis coefficient. Typically between 0.0 and 1.0. (Default: 0.97)

Returns:

Pre-emphasized waveform, with shape (…, N).

Return type:

torch.Tensor