Neural ODE with Temporal Convolution and Time Delay Neural Networks for Small-Footprint Keyword Spotting
This work addresses the need for efficient keyword spotting in resource-constrained devices, but it appears incremental as it adapts existing NODE methods to this domain.
The paper tackled the problem of small-footprint keyword spotting by proposing neural network models based on neural ordinary differential equations, resulting in a 68% reduction in model parameters compared to conventional models.
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.