UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-noise Ratio Condition

Autor:	Hao, Xiang, Su, Xiangdong, Wang, Zhiyu, Zhang, Hui, Batushiren
Rok vydání:	2020
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Sound Electrical Engineering and Systems Science - Signal Processing
Druh dokumentu:	Working Paper
DOI:	10.21437/Interspeech.2019-1567
Popis:	Speech enhancement at extremely low signal-to-noise ratio (SNR) condition is a very challenging problem and rarely investigated in previous works. This paper proposes a robust speech enhancement approach (UNetGAN) based on U-Net and generative adversarial learning to deal with this problem. This approach consists of a generator network and a discriminator network, which operate directly in the time domain. The generator network adopts a U-Net like structure and employs dilated convolution in the bottleneck of it. We evaluate the performance of the UNetGAN at low SNR conditions (up to -20dB) on the public benchmark. The result demonstrates that it significantly improves the speech quality and substantially outperforms the representative deep learning models, including SEGAN, cGAN fo SE, Bidirectional LSTM using phase-sensitive spectrum approximation cost function (PSA-BLSTM) and Wave-U-Net regarding Short-Time Objective Intelligibility (STOI) and Perceptual evaluation of speech quality (PESQ). Comment: Published in Interspeech 2019
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2010.15521 Zobrazit plný text záznamu View this record from Arxiv