Deep neural networks have shown excellent prospects in speech separation tasks. However, obtaining good results while keeping a low model complexity remains challenging in real-world applications. In this paper, we provide a bio-inspired efficient encoder-decoder architecture by mimicking the brain's top-down attention, called TDANet, with decreased model complexity without sacrificing performance. The top-down attention in TDANet is extracted by the global attention (GA) module and the cascaded local attention (LA) layers. The GA module takes multi-scale acoustic features as input to extract global attention signal, which then modulates features of different scales by direct top-down connections. The LA layers use features of adjacent layers as input to extract the local attention signal, which is used to modulate the lateral input in a top-down manner. On three benchmark datasets, TDANet consistently achieved competitive separation performance to previous state-of-the-art (SOTA) methods with higher efficiency. Specifically, TDANet's multiply-accumulate operations (MACs) are only 5\% of Sepformer, one of the previous SOTA models, and CPU inference time is only 10\% of Sepformer. In addition, a large-size version of TDANet obtained SOTA results on three datasets, with MACs still only 10\% of Sepformer and the CPU inference time only 24\% of Sepformer.

翻译：深度神经网络在语音分离任务中展现了优异的前景。然而，在实际应用中，如何在保持低模型复杂度的同时获得良好效果仍具挑战性。本文通过模仿大脑的自上而下注意力机制，提出了一种受生物启发的高效编码器-解码器架构——TDANet，在降低模型复杂度的同时不牺牲性能。TDANet中的自上而下注意力由全局注意力模块和级联局部注意力层提取。全局注意力模块以多尺度声学特征为输入，提取全局注意力信号，并通过直接自上而下的连接调节不同尺度的特征。局部注意力层以相邻层的特征为输入，提取局部注意力信号，用于以自上而下的方式调节侧向输入。在三个基准数据集上，TDANet始终以更高的效率取得了与先前最优方法相当的分离性能。具体而言，TDANet的乘累加运算量仅为先前最优模型之一Sepformer的5%，CPU推理时间仅为Sepformer的10%。此外，TDANet的大尺寸版本在三个数据集上取得了最优结果，其乘累加运算量仍仅为Sepformer的10%，CPU推理时间仅为Sepformer的24%。