Dense-tsnet: Dense Connected Two-stage Structure For Ultra-lightweight Speech Enhancement

Abstract

Speech enhancement aims to improve speech quality and intelligibility in noisy environments. Recent advancements have concentrated on deep neural networks, particularly employing the Two-Stage (TS) architecture to enhance feature extraction. However, the complexity and size of these models remain significant, which limits their applicability in resource-constrained scenarios. Designing models suitable for edge devices presents its own set of challenges. Narrow lightweight models often encounter performance bottlenecks due to uneven loss landscapes. Additionally, advanced operators such as Transformers or Mamba may lack the practical adaptability and efficiency that convolutional neural networks (CNNs) offer in real-world deployments. To address these challenges, we propose Dense-TSNet, an innovative ultra-lightweight speech enhancement network. Our approach employs a novel Dense Two-Stage (Dense-TS) architecture, which, compared to the classic Two-Stage architecture, ensures more robus

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylin2024dense

Related papers

• TFCN: Temporal-frequential Convolutional Network For Single-channel Speech Enhancement (2022)0.00
• Thlnet: Two-stage Heterogeneous Lightweight Network For Monaural Speech Enhancement (2023)0.00
• UL-UNAS: Ultra-lightweight U-nets For Real-time Speech Enhancement Via Network Architecture Search (2025)10.26
• Study Of Lightweight Transformer Architectures For Single-channel Speech Enhancement (2025)3.58
• Dynamically Slimmable Speech Enhancement Network With Metric-guided Training (2025)0.00
• TSTNN: Two-stage Transformer Based Neural Network For Speech Enhancement In The Time Domain (2021)16.73
• Speech Enhancement Deep-learning Architecture For Efficient Edge Processing (2024)0.00
• Cheapnet: Improving Light-weight Speech Enhancement Network By Projected Loss Function (2023)0.00