对比PLC:用于丢包隐蔽的对比学习
Contrast-PLC: Contrastive Learning for Packet Loss Concealment
摘要:
当可用上下文有限时,数据包丢失隐藏(PLC)在合理且自然地隐藏丢失内容方面具有挑战性。最近,基于深度学习的PLC算法已经证明了它们比传统算法的优越性,但它们的隐藏能力仍然主要限于最大120 ms的丢失。即使使用强大的基于GAN的生成模型,预测可能发生在音素内/音素之间的长突发丢失仍然非常具有挑战性。在本文中,我们提出了使用对比学习学习的损失鲁棒的语义表示PLC。设计了一种结合语义预测和基于GAN的生成模型的混合神经PLC结构,以验证其有效性。在Interspeech 2022 PLC Challenge盲测试集上的测试结果表明,该框架优于常用的UNet风格框架和没有对比学习的框架,特别是对于(120,220] ms的较长突发丢失。
英文摘要:
Packet loss concealment (PLC) is challenging in concealing missing contents both plausibly and naturally when there are only limited available context to use. Recently deep-learning based PLC algorithms have demonstrated their superiority over traditional counterparts; but their concealment ability is still mostly limited to a maximum of 120ms loss. Even with strong GAN-based generative models, it is still very challenging to predict long burst losses that could happen within/in-between phonemes. In this paper, we propose to use contrastive learning to learn a loss-robust semantic representation for PLC. A hybrid neural PLC architecture combining the semantic prediction and GAN-based generative model is designed to verify its effectiveness. Results on the blind test set of Interspeech2022 PLC Challenge show its superiority over commonly used UNet-style framework and the one without contrastive learning, especially for the longer burst loss at (120, 220] ms.
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。