articleIEEE Transactions on Audio Speech and Language ProcessingJan 1, 2026Closed access

UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Search

XRXiaobin RongLYLeyan YangDWDahan WangYHYuxiang HuCZChangbao Zhu

Institute of Acoustics · Nanjing University

Indexed incrossref

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.…

Citation impact

5
total citations
FWCI
191.29
Percentile
100%
References
56
Too recent for citation history.

Authors

7

Topics & keywords

Topics
Keywords
  • Leverage (statistics)
  • Boosting (machine learning)
  • Convolutional neural network
  • Architecture
  • Speech enhancement
  • Network architecture
  • Speech coding
  • Speech processing
No related works found for this paper.

Funding