# A Wavenet for Speech Denoising

## TL;DR

This paper introduces an end-to-end Wavenet-based speech denoising model that preserves phase information, improves computational efficiency, and outperforms traditional spectrogram-based methods like Wiener filtering.

## Contribution

It adapts Wavenet for speech denoising by removing autoregressive components, enabling parallel processing and directly modeling raw audio signals.

## Key findings

- Outperforms Wiener filtering in perceptual quality
- Significantly reduces computational complexity
- Supports parallel training and inference

## Abstract

Currently, most speech processing techniques use magnitude spectrograms as front-end and are therefore by default discarding part of the signal: the phase. In order to overcome this limitation, we propose an end-to-end learning method for speech denoising based on Wavenet. The proposed model adaptation retains Wavenet's powerful acoustic modeling capabilities, while significantly reducing its time-complexity by eliminating its autoregressive nature. Specifically, the model makes use of non-causal, dilated convolutions and predicts target fields instead of a single target sample. The discriminative adaptation of the model we propose, learns in a supervised fashion via minimizing a regression loss. These modifications make the model highly parallelizable during both training and inference. Both computational and perceptual evaluations indicate that the proposed method is preferred to Wiener filtering, a common method based on processing the magnitude spectrogram.