PAGAN: A Phase-Adapted Generative Adversarial Networks for Speech Enhancement
Peishuo Li, Zihang Jiang, Shouyi Yin, Dandan Song, Peng Ouyang, Leibo Liu, Shaojun Wei
Abstract
Deep neural networks (DNNs) are becoming more and more popular in speech enhancement. Most of DNN-based speech enhancement approaches currently operate on magnitude spectra and ignore the phase mismatch between noisy and clean speech which greatly limits the speech enhancement performance. This paper presents a new approach to solve the phase mismatch problem by training traditional DNN adversarially with a time-domain discriminator. Instead of estimating a more accurate phase, the DNN is trained to be more adapted to noisy phase and able to minimize the influence brought by the phase mismatch. We also propose a new evaluation metric to judge the degree of adaptation to noisy phase. Experimental results show that adding of time-domain discriminator yields a more phase-adapted generator and significantly improves the speech enhancement performance.
BibTeX
@inproceedings{icassp2020_paganaphaseadapt,
title = {PAGAN: A Phase-Adapted Generative Adversarial Networks for Speech Enhancement},
author = {Peishuo Li and Zihang Jiang and Shouyi Yin and Dandan Song and Peng Ouyang and Leibo Liu and Shaojun Wei},
booktitle = {ICASSP 2020},
year = {2020}
}