MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Data
| Autor: | George Close, Thomas Hain, Stefan Goetze |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
Sound (cs.SD) Computer Science - Machine Learning Audio and Speech Processing (eess.AS) FOS: Electrical engineering electronic engineering information engineering Computer Science - Sound Machine Learning (cs.LG) Electrical Engineering and Systems Science - Audio and Speech Processing |
| Popis: | 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% (3.05 vs 3.22 PESQ score), as well as better generalisation to unseen noise and speech. 5 pages, 4 figures, Accepted to EUSIPCO 2022 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|