{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ul-unas-ultra-lightweight-u-nets-for-real","title":"UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Search","arxiv_id":"2503.00340","date":"2025-03-01","proceeding":null,"authors":["Xiaobin Rong","DaHan Wang","Yuxiang Hu","Changbao Zhu","Kai Chen","Jing Lou"],"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 complexity, but also delivers competitive performance compared to recent baseline models that require substantially higher computational resources.","url_abs":"https://arxiv.org/abs/2503.00340v1","url_pdf":"https://arxiv.org/pdf/2503.00340v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ul-unas-ultra-lightweight-u-nets-for-real","repo_url":"https://github.com/Xiaobin-Rong/ul-unas","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"prelu","method_name":"PReLU"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}