A Wavenet for Speech Denoising
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.
Cite
@article{arxiv.1706.07162,
title = {A Wavenet for Speech Denoising},
author = {Dario Rethage and Jordi Pons and Xavier Serra},
journal= {arXiv preprint arXiv:1706.07162},
year = {2018}
}
Comments
In proceedings of the 43rd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2018). Code: https://github.com/drethage/speech-denoising-wavenet - Audio examples: http://jordipons.me/apps/speech-denoising-wavenet/