functional_add_noise_shaping {torchaudio}

Noise Shaping (functional)

Description

Noise shaping is calculated by error: error[n] = dithered[n] - original[n] noise_shaped_waveform[n] = dithered[n] + error[n-1]

Usage

functional_add_noise_shaping(dithered_waveform, waveform)

Arguments

dithered_waveform

(Tensor) dithered

waveform

(Tensor) original

Value

tensor of the noise shaped waveform