论文标题
具有时间卷积和时间延迟神经网络的神经颂
Neural ODE with Temporal Convolution and Time Delay Neural Networks for Small-Footprint Keyword Spotting
论文作者
论文摘要
在本文中，我们提出了基于针对小脚印关键字点（KWS）的神经普通微分方程（节点）的神经网络模型。我们提出了将节点应用于KWS的技术，从而使基于节点的网络的批处理标准化并减少推理期间的计算数量成为可能。最后，我们表明，所提出的模型的模型参数数量比常规KWS模型的模型参数较小68％。
In this paper, we propose neural network models based on the neural ordinary differential equation (NODE) for small-footprint keyword spotting (KWS). We present techniques to apply NODE to KWS that make it possible to adopt Batch Normalization to NODE-based network and to reduce the number of computations during inference. Finally, we show that the number of model parameters of the proposed model is smaller by 68% than that of the conventional KWS model.
