论文标题
LCSM：立体声音回声取消的轻量级复杂频谱映射框架
LCSM: A Lightweight Complex Spectral Mapping Framework for Stereophonic Acoustic Echo Cancellation
论文作者
论文摘要
传统的自适应算法在处理立体声音回声取消（SAEC）时将面临非唯一性问题。在本文中，我们首先提出了一个有效的多输入和多输出（MIMO）方案，基于深度学习，以一次过滤所有麦克风信号的回声。然后，我们采用轻巧的复杂频谱映射框架（LCSM）进行端到端的SAEC，而无需去扬声器信号进行反相关的预处理。使用场地卷积和通过渠道的空间建模来确保保留近端信号信息。最后，跨域损耗函数设计用于更好的概括能力。在各种未经训练的条件下评估了实验，结果表明LCSM明显优于先前的方法。此外，拟议的因果框架只有55万个参数，远低于类似的基于深度学习的方法，这对于资源有限的设备很重要。
The traditional adaptive algorithms will face the non-uniqueness problem when dealing with stereophonic acoustic echo cancellation (SAEC). In this paper, we first propose an efficient multi-input and multi-output (MIMO) scheme based on deep learning to filter out echoes from all microphone signals at once. Then, we employ a lightweight complex spectral mapping framework (LCSM) for end-to-end SAEC without decorrelation preprocessing to the loudspeaker signals. Inplace convolution and channel-wise spatial modeling are utilized to ensure the near-end signal information is preserved. Finally, a cross-domain loss function is designed for better generalization capability. Experiments are evaluated on a variety of untrained conditions and results demonstrate that the LCSM significantly outperforms previous methods. Moreover, the proposed causal framework only has 0.55 million parameters, much less than the similar deep learning-based methods, which is important for the resource-limited devices.
