Log In Sign Up

Encoder-Decoder Neural Architecture Optimization for Keyword Spotting

by   Tong Mo, et al.

Keyword spotting aims to identify specific keyword audio utterances. In recent years, deep convolutional neural networks have been widely utilized in keyword spotting systems. However, their model architectures are mainly based on off-the shelfbackbones such as VGG-Net or ResNet, instead of specially designed for the task. In this paper, we utilize neural architecture search to design convolutional neural network models that can boost the performance of keyword spotting while maintaining an acceptable memory footprint. Specifically, we search the model operators and their connections in a specific search space with Encoder-Decoder neural architecture optimization. Extensive evaluations on Google's Speech Commands Dataset show that the model architecture searched by our approach achieves a state-of-the-art accuracy of over 97


page 1

page 2

page 3

page 4


Neural Architecture Search For Keyword Spotting

Deep neural networks have recently become a popular solution to keyword ...

Performance-Oriented Neural Architecture Search

Hardware-Software Co-Design is a highly successful strategy for improvin...

Stochastic Adaptive Neural Architecture Search for Keyword Spotting

The problem of keyword spotting i.e. identifying keywords in a real-time...

EfficientNet-Absolute Zero for Continuous Speech Keyword Spotting

Keyword spotting is a process of finding some specific words or phrases ...

AutoDispNet: Improving Disparity Estimation with AutoML

Much research work in computer vision is being spent on optimizing exist...

SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

Convolutional neural networks typically encode an input image into a ser...

AutoKWS: Keyword Spotting with Differentiable Architecture Search

Smart audio devices are gated by an always-on lightweight keyword spotti...