UL-UNAS: Ultra-lightweight U-nets For Real-time Speech Enhancement Via Network Architecture Search

Abstract

Lightweight models are essential for real-time speech enhancement applications. In recent years, there has been a growing trend toward developing increasingly compact models for speech enhancement. In this paper, we propose an Ultra-Lightweight U-net optimized by Network Architecture Search (UL-UNAS), which is suitable for implementation in low-footprint devices. Firstly, we explore the application of various efficient convolutional blocks within the U-Net framework to identify the most promising candidates. Secondly, we introduce two boosting components to enhance the capacity of these convolutional blocks: a novel activation function named affine PReLU and a causal time-frequency attention module. Furthermore, we leverage neural architecture search to discover an optimal architecture within our carefully designed search space. By integrating the above strategies, UL-UNAS not only significantly outperforms the latest ultra-lightweight models with the same or lower computational comple

Stats

• citations5
• S2 citations—
• github stars161
• HF likes0
• heat score10.26
• arxiv keyrong2025ul

Related papers

• Dense-tsnet: Dense Connected Two-stage Structure For Ultra-lightweight Speech Enhancement (2024)0.00
• Thlnet: Two-stage Heterogeneous Lightweight Network For Monaural Speech Enhancement (2023)0.00
• Improved Speech Enhancement With The Wave-u-net (2018)0.00
• Lisennet: Lightweight Sub-band And Dual-path Modeling For Real-time Speech Enhancement (2024)9.03
• Relunet: Relative Channel Fusion U-net For Multichannel Speech Enhancement (2024)0.00
• Using Recurrences In Time And Frequency Within U-net Architecture For Speech Enhancement (2018)8.35
• Cheapnet: Improving Light-weight Speech Enhancement Network By Projected Loss Function (2023)0.00
• Single-channel Speech Enhancement With Deep Complex U-networks And Probabilistic Latent Space Models (2023)5.24