AudioRepInceptionNeXt：一种用于高效音频识别的轻量级单流架构
AudioRepInceptionNeXt: A lightweight single-stream architecture for efficient audio recognition
AI总结：
提出轻量级单流架构AudioRepInceptionNeXt，通过级联多分支深度卷积分离时频处理并重参数化，在保持精度的同时大幅降低计算与内存开销。
摘要：
近期研究已成功将基于视觉的卷积神经网络（CNN）架构应用于使用Mel-Spectrograms的音频识别任务。然而，这些CNN具有较高的计算成本和内存需求，限制了其在低端边缘设备上的部署。受InceptionNeXt和ConvNeXt等高效视觉模型成功的启发，我们提出了一种单流架构AudioRepInceptionNeXt。其基础构建块将具有递减尺度k x k核的并行多分支深度卷积分解为两个多分支深度卷积的级联。第一个多分支由并行的多尺度1 x k深度卷积层组成，随后是采用并行多尺度k x 1深度卷积层的类似多分支。这减少了计算和内存占用，同时分离了Mel-Spectrograms的时间和频率处理。大核捕获全局频率和长活动，而小核获取局部频率和短活动。我们还在推理期间对多分支设计进行重参数化，以在不损失精度的情况下进一步提升速度。实验表明，与Slow-Fast等最先进的CNN相比，AudioRepInceptionNeXt将参数和计算量减少了50%以上，推理速度提升了1.28倍，同时保持了相当的精度。它还在各种音频识别任务中表现出鲁棒的学习能力。代码可在https://github.com/StevenLauHKHK/AudioRepInceptionNeXt获取。
英文摘要：
Recent research has successfully adapted vision-based convolutional neural network (CNN) architectures for audio recognition tasks using Mel-Spectrograms. However, these CNNs have high computational costs and memory requirements, limiting their deployment on low-end edge devices. Motivated by the success of efficient vision models like InceptionNeXt and ConvNeXt, we propose AudioRepInceptionNeXt, a single-stream architecture. Its basic building block breaks down the parallel multi-branch depth-wise convolutions with descending scales of k x k kernels into a cascade of two multi-branch depth-wise convolutions. The first multi-branch consists of parallel multi-scale 1 x k depth-wise convolutional layers followed by a similar multi-branch employing parallel multi-scale k x 1 depth-wise convolutional layers. This reduces computational and memory footprint while separating time and frequency processing of Mel-Spectrograms. The large kernels capture global frequencies and long activities, while small kernels get local frequencies and short activities. We also reparameterize the multi-branch design during inference to further boost speed without losing accuracy. Experiments show that AudioRepInceptionNeXt reduces parameters and computations by 50%+ and improves inference speed 1.28x over state-of-the-art CNNs like the Slow-Fast while maintaining comparable accuracy. It also learns robustly across a variety of audio recognition tasks. Codes are available at https://github.com/StevenLauHKHK/AudioRepInceptionNeXt.
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。
