DeepAI
Log In Sign Up

MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Data

03/23/2022
by   George Close, et al.
0

Training of speech enhancement systems often does not incorporate knowledge of human perception and thus can lead to unnatural sounding results. Incorporating psychoacoustically motivated speech perception metrics as part of model training via a predictor network has recently gained interest. However, the performance of such predictors is limited by the distribution of metric scores that appear in the training data. In this work, we propose MetricGAN+/- (an extension of MetricGAN+, one such metric-motivated system) which introduces an additional network - a "de-generator" which attempts to improve the robustness of the prediction network (and by extension of the generator) by ensuring observation of a wider range of metric scores in training. Experimental results on the VoiceBank-DEMAND dataset show relative improvement in PESQ score of 3.8 generalisation to unseen noise and speech.

READ FULL TEXT
04/08/2021

MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement

The discrepancy between the cost function used for training a speech enh...
12/18/2017

Language and Noise Transfer in Speech Enhancement Generative Adversarial Network

Speech enhancement deep learning systems usually require large amounts o...
05/13/2019

MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement

Adversarial loss in a conditional generative adversarial network (GAN) i...
02/17/2021

Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder

Recently, a generative variational autoencoder (VAE) has been proposed f...
03/28/2017

SEGAN: Speech Enhancement Generative Adversarial Network

Current speech enhancement techniques operate on the spectral domain and...