arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2211.04071cs.SDeess.AS
收藏

利用预测网络提升实时全频带盲丢包隐藏性能

Improving performance of real-time full-band blind packet-loss concealment with predictive network

NamiTech JSC(纳美科技公司);Nanyang Technological University(南洋理工大学)

Viet-Anh Nguyen, Anh H. T. Nguyen, Andy W. H. Khong

AI总结:

提出实时全频带递归网络(FRN)用于盲丢包隐藏,在48kHz下利用先前输出减轻伪影,无需丢失掩码,性能优于离线基线和挑战赛最佳。

摘要:

丢包隐藏(PLC)是一种用于改善因网络状况不佳或音频处理管线中下溢/溢出导致的语音退化的工具。我们提出一种实时递归方法,利用先前输出减轻丢失数据包产生的伪影,而无需预先知晓丢失掩码。所提出的全频带递归网络(FRN)模型在48 kHz下运行,适用于高质量电信应用。实验结果凸显了FRN相较于离线非因果基线以及近期PLC挑战中表现最佳者的优越性。

英文摘要:

Packet loss concealment (PLC) is a tool for enhancing speech degradation caused by poor network conditions or underflow/overflow in audio processing pipelines. We propose a real-time recurrent method that leverages previous outputs to mitigate artefact of lost packets without the prior knowledge of loss mask. The proposed full-band recurrent network (FRN) model operates at 48 kHz, which is suitable for high-quality telecommunication applications. Experiment results highlight the superiority of FRN over an offline non-causal baseline and a top performer in a recent PLC challenge.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑