Unetgan: A Robust Speech Enhancement Approach In Time Domain For Extremely Low Signal-to-noise Ratio Condition

Abstract

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

Stats

• citations33
• S2 citations—
• github stars0
• HF likes0
• heat score11.49
• arxiv keyhao2020unetgan

Related papers

• Metricgan-u: Unsupervised Speech Enhancement/ Dereverberation Based Only On Noisy/ Reverberated Speech (2021)11.67
• Conditional Generative Adversarial Networks For Speech Enhancement And Noise-robust Speaker Verification (2017)16.03
• SEGAN: Speech Enhancement Generative Adversarial Network (2017)21.85
• Gan-based Speech Enhancement For Low SNR Using Latent Feature Conditioning (2024)5.24
• A Comparative Evaluation Of Deep Learning Models For Speech Enhancement In Real-world Noisy Environments (2025)0.00
• Speech Enhancement Deep-learning Architecture For Efficient Edge Processing (2024)0.00
• Multi-metric Optimization Using Generative Adversarial Networks For Near-end Speech Intelligibility Enhancement (2021)8.60
• Tdcgan: Temporal Dilated Convolutional Generative Adversarial Network For End-to-end Speech Enhancement (2020)0.00