AddNoise

class torchaudio.transforms.AddNoise(*args, **kwargs)

Scales and adds noise to waveform per signal-to-noise ratio. See torchaudio.functional.add_noise() for more details.

forward(waveform: Tensor, noise: Tensor, snr: Tensor, lengths: Optional[Tensor] = None) → Tensor

Parameters:

• waveform (torch.Tensor) – Input waveform, with shape (…, L).

• noise (torch.Tensor) – Noise, with shape (…, L) (same shape as waveform).

• snr (torch.Tensor) – Signal-to-noise ratios in dB, with shape (…,).

• lengths (torch.Tensor or None, optional) – Valid lengths of signals in waveform and noise,

• ` (with shape) –

• (Default (elements in waveform and noise are treated as valid.) – None)

Returns:

Result of scaling and adding noise to waveform, with shape (…, L) (same shape as waveform).

Return type:

torch.Tensor