Neural ODE with Temporal Convolution and Time Delay Neural Networks for Small-Footprint Keyword Spotting

08/01/2020
by   Hiroshi Fuketa, et al.
0

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

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/01/2021

A Separable Temporal Convolution Neural Network with Attention for Small-Footprint Keyword Spotting

Keyword spotting (KWS) on mobile devices generally requires a small memo...
research
10/20/2020

Small-Footprint Keyword Spotting with Multi-Scale Temporal Convolution

Keyword Spotting (KWS) plays a vital role in human-computer interaction ...
research
08/27/2021

Separable Temporal Convolution plus Temporally Pooled Attention for Lightweight High-performance Keyword Spotting

Keyword spotting (KWS) on mobile devices generally requires a small memo...
research
04/21/2023

Small-footprint slimmable networks for keyword spotting

In this work, we present Slimmable Neural Networks applied to the proble...
research
04/20/2020

Towards Understanding Normalization in Neural ODEs

Normalization is an important and vastly investigated technique in deep ...
research
02/27/2019

ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs

Residual neural networks can be viewed as the forward Euler discretizati...
research
01/03/2021

Neural Networks for Keyword Spotting on IoT Devices

We explore Neural Networks (NNs) for keyword spotting (KWS) on IoT devic...

Please sign up or login with your details

Forgot password? Click here to reset