GAN-Based Speech Enhancement for Low SNR Using Latent Feature Conditioning

2024/10/17 by Shrishti Saha Shetu, Shetu, Shrishti Saha, Emanuël A. P. Habets +3 · 5 citations
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Signal Processing (eess.SP) #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2410.13599

openalex publication_date 2024/10/17 · openalex created_date 2024/10/21 · openalex updated_date 2026/07/28

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

Cited by

• AUREXA-SE: Audio-Visual Unified Representation Exchange Architecture with Cross-Attention and Squeezeformer for Speech Enhancement
• GAN-Based Multi-Microphone Spatial Target Speaker Extraction
• Leveraging Discriminative Latent Representations for Conditioning GAN-Based Speech Enhancement
• Few-step Adversarial Schrödinger Bridge for Generative Speech Enhancement
• Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation

Related

• Leveraging Discriminative Latent Representations for Conditioning GAN-Based Speech Enhancement
• Time-domain Speech Enhancement with Generative Adversarial Learning
• Tdcgan: Temporal Dilated Convolutional Generative Adversarial Network for End-to-end Speech Enhancement
• TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis
• Towards Generalized Speech Enhancement with Generative Adversarial Networks