Gan-based Speech Enhancement For Low SNR Using Latent Feature Conditioning

Abstract

Enhancing speech quality under adverse SNR conditions remains a significant challenge for discriminative deep neural network (DNN)-based approaches. In this work, we propose DisCoGAN, which is a time-frequency-domain generative adversarial network (GAN) conditioned by the latent features of a discriminative model pre-trained for speech enhancement in low SNR scenarios. Our proposed method achieves superior performance compared to state-of-the-arts discriminative methods and also surpasses end-to-end (E2E) trained GAN models. We also investigate the impact of various configurations for conditioning the proposed GAN model with the discriminative model and assess their influence on enhancing speech quality

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keyshetu2024gan

Related papers

• Tdcgan: Temporal Dilated Convolutional Generative Adversarial Network For End-to-end Speech Enhancement (2020)0.00
• Dynamic Attention Based Generative Adversarial Network With Phase Post-processing For Speech Enhancement (2020)0.00
• Unetgan: A Robust Speech Enhancement Approach In Time Domain For Extremely Low Signal-to-noise Ratio Condition (2020)11.49
• Hifi-gan: High-fidelity Denoising And Dereverberation Based On Speech Deep Features In Adversarial Networks (2020)0.00
• DCCRGAN: Deep Complex Convolution Recurrent Generator Adversarial Network For Speech Enhancement (2020)0.00
• Multi-metric Optimization Using Generative Adversarial Networks For Near-end Speech Intelligibility Enhancement (2021)8.60
• Conditional Generative Adversarial Networks For Speech Enhancement And Noise-robust Speaker Verification (2017)16.03
• Towards Generalized Speech Enhancement With Generative Adversarial Networks (2019)10.35