基于循环融合空洞卷积与通道注意力的高效语音分离网络
An Efficient Speech Separation Network Based on Recurrent Fusion Dilated Convolution and Channel Attention
AI总结：
针对卷积网络感受野有限、Transformer网络计算成本高的问题，提出结合空洞卷积、多尺度融合与通道注意力的ARFDCN语音分离网络，实现了性能与计算效率的良好平衡，可作为主流模型的实用替代方案。
摘要：
我们提出了一种高效的语音分离神经网络ARFDCN，该网络结合了空洞卷积、多尺度融合（MSF）和通道注意力，以克服基于卷积的网络感受野有限以及基于transformer的网络计算成本高的问题。所提出的网络架构基于编码器-解码器结构。通过使用扩张值逐渐增大的空洞卷积来学习局部和全局特征，并在相邻阶段对其进行融合，该模型能够学习丰富的特征内容。同时，通过在网络中加入通道注意力模块，模型可以提取通道权重，学习更重要的特征，从而提升其表达能力和鲁棒性。实验结果表明，该模型在性能和计算效率之间实现了良好的平衡，是实际应用中现有主流模型的一种有潜力的替代方案。
英文摘要：
We present an efficient speech separation neural network, ARFDCN, which combines dilated convolutions, multi-scale fusion (MSF), and channel attention to overcome the limited receptive field of convolution-based networks and the high computational cost of transformer-based networks. The suggested network architecture is encoder-decoder based. By using dilated convolutions with gradually increasing dilation value to learn local and global features and fusing them at adjacent stages, the model can learn rich feature content. Meanwhile, by adding channel attention modules to the network, the model can extract channel weights, learn more important features, and thus improve its expressive power and robustness. Experimental results indicate that the model achieves a decent balance between performance and computational efficiency, making it a promising alternative to current mainstream models for practical applications.
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。
