{"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/fspen-an-ultra-lightweight-network-for-real","title":"FSPEN: AN ULTRA-LIGHTWEIGHT NETWORK FOR REAL TIME SPEECH ENAHNCMENT","arxiv_id":null,"date":"2024-04-15","proceeding":"Conference 2024 4","authors":["Lei Yang1","Wei Liu1","Ruijie Meng1","Gunwoo Lee2","Soonho Baek2","Han-gil Moon2"],"abstract":"Deep learning-based speech enhancement methods have shown promising result in recent years. However, in practical applications, the model size and computational complexity are important factors that limit their use in end-products.\r\nTherefore, in products that require real-time speech enhancement with limited resources, such as TWS headsets, hearing\r\naids, IoT devices, etc., ultra-lightweight models are necessary. In this paper, an ultra-lightweight network FSPEN is proposed for real-time speech enhancement task. We propose a full-band and sub-band network structure for extracting global and local features, and an inter-frame path extension method that can enhance network modeling capacity while preserving complexity. Experiments demonstrate that the proposed FSPEN achieves a performance of PESQ 2.97 on the VoiceBank+Demand dataset at 89M multiply-accumulate operation per second (MAC) and 79k parameters.","url_abs":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10446016","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10446016","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":"fspen-an-ultra-lightweight-network-for-real","repo_url":"https://github.com/gitwukeyi/FSPEN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-enhancement-on-demand","task":"Speech Enhancement","dataset":"VoiceBank + DEMAND","model":"FSPEN","rank_in_archive_order":34,"of":42,"metrics":{"PESQ (wb)":"2.97","Para. (M)":"0.079","STOI":"0.942"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}