Thanks to Deep Neural Networks (DNNs), the accuracy of Keyword Spotting (KWS) has made substantial progress. However, as KWS systems are usually implemented on edge devices, energy efficiency becomes a critical requirement besides performance. Here, we take advantage of spiking neural networks' energy efficiency and propose an end-to-end lightweight KWS model. The model consists of two innovative modules: 1) Global-Local Spiking Convolution (GLSC) module and 2) Bottleneck-PLIF module. Compared to the hand-crafted feature extraction methods, the GLSC module achieves speech feature extraction that is sparser, more energy-efficient, and yields better performance. The Bottleneck-PLIF module further processes the signals from GLSC with the aim to achieve higher accuracy with fewer parameters. Extensive experiments are conducted on the Google Speech Commands Dataset (V1 and V2). The results show our method achieves competitive performance among SNN-based KWS models with fewer parameters.

通过利用脉冲神经网络的能效优势，我们提出了一种端到端轻量级的关键词识别模型，其中包括全局-局部脉冲卷积模块和瓶颈-脉冲增强模块，通过精心设计的特征提取方法，实现了更稀疏、更能源高效且性能更好的语音特征提取，进一步通过瓶颈-脉冲增强模块处理信号以实现更高的准确性和更少的参数。在Google语音命令数据集（V1和V2）上进行了大量实验，结果表明我们的方法在脉冲神经网络关键词识别模型中以更少的参数实现了竞争性能。

全局-局部卷积与脉冲神经网络在能效关键词检测中的应用