MetricGAN+/-: increasing robustness of noise reduction on unseen data

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 Metric-GAN+, one such metric-motivated system) which introduces an additional network - a “de-generator” 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% (3.05 vs. 3.22 PESQ score), as well as better generalisation to unseen noise and speech signals.