Neural ODE With Temporal Convolution And Time Delay Neural Networks For Small-footprint Keyword Spotting

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfuketa2020neural

Related papers

• A Separable Temporal Convolution Neural Network With Attention For Small-footprint Keyword Spotting (2021)0.00
• Small-footprint Keyword Spotting With Multi-scale Temporal Convolution (2020)0.00
• Small-footprint Keyword Spotting Using Deep Neural Network And Connectionist Temporal Classifier (2017)0.00
• Small-footprint Keyword Spotting With Graph Convolutional Network (2019)10.48
• Predicting Detection Filters For Small Footprint Open-vocabulary Keyword Spotting (2019)9.92
• Efficient Keyword Spotting Using Time Delay Neural Networks (2018)10.21
• Separable Temporal Convolution Plus Temporally Pooled Attention For Lightweight High-performance Keyword Spotting (2021)0.00
• Efficient Keyword Spotting Using Dilated Convolutions And Gating (2018)13.84