arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.03100cs.SDeess.AS
收藏

一种用于丢包隐藏的对抗性自动编码算法

Adversarial Auto-Encoding for Packet Loss Concealment

Dolby Laboratories(杜比实验室)

Santiago Pascual, Joan Serrà, Jordi Pons

摘要:

像IP语音这样的通信技术在受限的实时条件下运行,语音数据包会受到网络延迟和丢失的影响。在这种情况下,分组丢失隐藏(PLC)算法重建丢失的帧,直到接收到新的真实分组。最近,自回归深度神经网络已被证明超过PLC的信号处理方法的质量,特别是超过60毫秒的长期预测。在这项工作中,我们提出了一个非自回归对抗自编码器,命名为PLAAE,在波形域中执行实时PLC。PLAAE具有因果卷积结构,它以自动编码器的方式学习,在对抗性损失的帮助下重建具有间隙的信号。在推理过程中,它能够在单个前馈步骤中预测这种间隙的平滑和连贯的延续,而不是自回归模型。我们的评估强调了PLAAE在频谱和语调重建、感知质量和可懂度方面优于两种经典PLC和两种深度自回归模型。

英文摘要:

Communication technologies like voice over IP operate under constrained real-time conditions, with voice packets being subject to delays and losses from the network. In such cases, the packet loss concealment (PLC) algorithm reconstructs missing frames until a new real packet is received. Recently, autoregressive deep neural networks have been shown to surpass the quality of signal processing methods for PLC, specially for long-term predictions beyond 60 ms. In this work, we propose a non-autoregressive adversarial auto-encoder, named PLAAE, to perform real-time PLC in the waveform domain. PLAAE has a causal convolutional structure, and it learns in an auto-encoder fashion to reconstruct signals with gaps, with the help of an adversarial loss. During inference, it is able to predict smooth and coherent continuations of such gaps in a single feed-forward step, as opposed to autoregressive models. Our evaluation highlights the superiority of PLAAE over two classic PLCs and two deep autoregressive models in terms of spectral and intonation reconstruction, perceptual quality, and intelligibility.

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。

↑