流plc：基于流匹配的高效丢包隐藏

IF 3.2 2区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

IEEE Signal Processing Letters Pub Date : 2025-03-20 DOI:10.1109/LSP.2025.3553421

Da-Hee Yang;Joon-Hyuk Chang

{"title":"流plc：基于流匹配的高效丢包隐藏","authors":"Da-Hee Yang;Joon-Hyuk Chang","doi":"10.1109/LSP.2025.3553421","DOIUrl":null,"url":null,"abstract":"Recent advancements in packet loss concealment (PLC) have introduced diffusion-based generative models that offer high-quality audio reconstruction. However, their high computational costs make them impractical for real-time applications. In this letter, we present Flow-PLC, an efficient PLC model based on the flow-matching framework, designed to address these computational challenges. Flow-PLC achieves a remarkable 23× reduction in inference time compared to diffusion-based PLC models, requiring only five sampling steps to achieve near-optimal reconstruction. By significantly reducing computational complexity while maintaining high-quality results, Flow-PLC represents a substantial advancement in the development of efficient and practical generative PLC systems.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1430-1434"},"PeriodicalIF":3.2000,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Flow-PLC: Towards Efficient Packet Loss Concealment With Flow Matching\",\"authors\":\"Da-Hee Yang;Joon-Hyuk Chang\",\"doi\":\"10.1109/LSP.2025.3553421\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recent advancements in packet loss concealment (PLC) have introduced diffusion-based generative models that offer high-quality audio reconstruction. However, their high computational costs make them impractical for real-time applications. In this letter, we present Flow-PLC, an efficient PLC model based on the flow-matching framework, designed to address these computational challenges. Flow-PLC achieves a remarkable 23× reduction in inference time compared to diffusion-based PLC models, requiring only five sampling steps to achieve near-optimal reconstruction. By significantly reducing computational complexity while maintaining high-quality results, Flow-PLC represents a substantial advancement in the development of efficient and practical generative PLC systems.\",\"PeriodicalId\":13154,\"journal\":{\"name\":\"IEEE Signal Processing Letters\",\"volume\":\"32 \",\"pages\":\"1430-1434\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2025-03-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Signal Processing Letters\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10935651/\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Signal Processing Letters","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10935651/","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

摘要

最近在丢包隐藏（PLC）方面的进展引入了基于扩散的生成模型，提供高质量的音频重建。然而，它们的高计算成本使得它们在实时应用中不切实际。在这封信中，我们提出了Flow-PLC，一种基于流匹配框架的高效PLC模型，旨在解决这些计算挑战。与基于扩散的PLC模型相比，Flow-PLC的推理时间减少了23倍，只需要5个采样步骤就可以实现近乎最佳的重建。通过显著降低计算复杂性，同时保持高质量的结果，Flow-PLC代表了高效实用的生成式PLC系统发展的实质性进步。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Flow-PLC: Towards Efficient Packet Loss Concealment With Flow Matching

Recent advancements in packet loss concealment (PLC) have introduced diffusion-based generative models that offer high-quality audio reconstruction. However, their high computational costs make them impractical for real-time applications. In this letter, we present Flow-PLC, an efficient PLC model based on the flow-matching framework, designed to address these computational challenges. Flow-PLC achieves a remarkable 23× reduction in inference time compared to diffusion-based PLC models, requiring only five sampling steps to achieve near-optimal reconstruction. By significantly reducing computational complexity while maintaining high-quality results, Flow-PLC represents a substantial advancement in the development of efficient and practical generative PLC systems.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

IEEE Signal Processing Letters 工程技术-工程：电子与电气

CiteScore

7.40

自引率

12.80%

发文量

339

审稿时长

2.8 months

期刊介绍： The IEEE Signal Processing Letters is a monthly, archival publication designed to provide rapid dissemination of original, cutting-edge ideas and timely, significant contributions in signal, image, speech, language and audio processing. Papers published in the Letters can be presented within one year of their appearance in signal processing conferences such as ICASSP, GlobalSIP and ICIP, and also in several workshop organized by the Signal Processing Society.