The ICASSP 2024 Audio Deep Packet Loss Concealment Grand Challenge

IF 2.7 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC IEEE open journal of signal processing Pub Date : 2025-01-07 DOI:10.1109/OJSP.2025.3526552
Lorenz Diener;Solomiya Branets;Ando Saabas;Ross Cutler
{"title":"The ICASSP 2024 Audio Deep Packet Loss Concealment Grand Challenge","authors":"Lorenz Diener;Solomiya Branets;Ando Saabas;Ross Cutler","doi":"10.1109/OJSP.2025.3526552","DOIUrl":null,"url":null,"abstract":"Audio packet loss concealment hides gaps in VoIP audio streams caused by network packet loss. It operates in real-time with low computational requirements and latency, as demanded by modern communication systems. With the ICASSP 2024 Audio Deep Packet Loss Concealment Grand Challenge, we build on the success of the previous Audio PLC Challenge held at INTERSPEECH 2022. For the 2024 challenge at ICASSP, we update the challenge by introducing an overall harder blind evaluation set and extending the task from wideband to fullband audio, in keeping with current trends in internet telephony. In addition to the Word Accuracy metric, we also use a questionnaire based on an extension of ITU-T P.804 to more closely evaluate the performance of systems specifically on the PLC task. We evaluate a total of 9 systems submitted by different academic and industry teams, 8 of which satisfy the strict real-time performance requirements of the challenge, using both P.804 and Word Accuracy evaluations. Two systems share first place, with one of the systems having the advantage in terms of naturalness, while the other wins in terms of intelligibility. These systems are the current state of the art for Deep PLC.","PeriodicalId":73300,"journal":{"name":"IEEE open journal of signal processing","volume":"6 ","pages":"231-237"},"PeriodicalIF":2.7000,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10830479","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE open journal of signal processing","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10830479/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

Audio packet loss concealment hides gaps in VoIP audio streams caused by network packet loss. It operates in real-time with low computational requirements and latency, as demanded by modern communication systems. With the ICASSP 2024 Audio Deep Packet Loss Concealment Grand Challenge, we build on the success of the previous Audio PLC Challenge held at INTERSPEECH 2022. For the 2024 challenge at ICASSP, we update the challenge by introducing an overall harder blind evaluation set and extending the task from wideband to fullband audio, in keeping with current trends in internet telephony. In addition to the Word Accuracy metric, we also use a questionnaire based on an extension of ITU-T P.804 to more closely evaluate the performance of systems specifically on the PLC task. We evaluate a total of 9 systems submitted by different academic and industry teams, 8 of which satisfy the strict real-time performance requirements of the challenge, using both P.804 and Word Accuracy evaluations. Two systems share first place, with one of the systems having the advantage in terms of naturalness, while the other wins in terms of intelligibility. These systems are the current state of the art for Deep PLC.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
ICASSP 2024 音频深度丢包隐蔽大挑战
音频丢包隐藏隐藏了VoIP音频流中由于网络丢包而产生的空隙。根据现代通信系统的要求,它以低计算需求和低延迟实时运行。通过ICASSP 2024音频深度丢包隐藏大挑战,我们建立在之前在INTERSPEECH 2022举行的音频PLC挑战的成功基础上。对于ICASSP的2024年挑战,我们通过引入一个整体更难的盲评估集并将任务从宽带扩展到全频段音频来更新挑战,以保持当前互联网电话的趋势。除了Word精度度量,我们还使用基于ITU-T P.804扩展的问卷来更密切地评估系统的性能,特别是在PLC任务上。我们总共评估了来自不同学术和行业团队提交的9个系统,其中8个系统满足了挑战的严格实时性能要求,使用了P.804和Word准确性评估。两个系统共享第一名,其中一个系统在自然性方面具有优势,而另一个系统在可理解性方面获胜。这些系统是目前最先进的深度PLC。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
5.30
自引率
0.00%
发文量
0
审稿时长
22 weeks
期刊最新文献
List of Reviewers Identifiability Conditions for Acoustic Feedback Cancellation With the Two-Channel Adaptive Feedback Canceller Algorithm Embracing Cacophony: Explaining and Improving Random Mixing in Music Source Separation Common-Gain Autoencoder Network for Binaural Speech Enhancement LEMON: Localized Editing With Mesh Optimization and Neural Shaders
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1